[ { "id": "RAOULZADEH-2026-STROKES2DEFORM", "type_id": "journalpaper", "tu_id": null, "repositum_id": null, "title": "Strokes2Deform: Physics-informed learning of deformation fields on 3D stroke clouds", "date": "2026-08", "abstract": "In the 3D architectural design process, deformation analysis of a designed object is a fundamental step. However, such a step is usually inaccessible to designers in the early sketching phase, limiting designers’ ability to reason about the shape’s structural stability. To bridge this gap, we propose Strokes2Deform, an end-to-end learning-based model that enables deformation-aware 3D sketching, requiring neither (surface) reconstruction nor (physical) simulation. Our physics-informed neural network takes as input a 3D sketch stroke cloud and user-specified boundary conditions, and directly predicts the induced deformation field on the 3D stroke cloud. Key to our method is: (i) a synthetic dataset of 40K 3D sketch–deformation pairs of architectural thin-shell structures and their corresponding deformation fields derived from Finite Element (FE) analysis, (ii) the use of fVDB to encode 3D sketch stroke clouds and their per-point features into sparse voxel grids with attributes, and leveraging its differentiable splatting and sampling operators for bidirectional point–voxel mappings, (iii) a dual-head neural network architecture that decouples deformation field prediction into unit-length displacement vectors and scalar displacement magnitudes, and (iv) our physics-informed loss functions derived from thin-shell deformation principles. We validate our method through extensive experiments, demonstrating accurate deformation prediction across sketches of varying complexity and strong agreement with reference deformations derived from FE simulations.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "name": "RAOULZADEH-2026-STROKES2DEFORM-image.jpeg", "type": "image/jpeg", "size": 309502, "path": "Publication:RAOULZADEH-2026-STROKES2DEFORM", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/RAOULZADEH-2026-STROKES2DEFORM-image.jpeg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/RAOULZADEH-2026-STROKES2DEFORM-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5233, 5613, 5614, 1799, 193 ], "articleno": "104629", "date_from": "2026-06-01", "date_to": "2026-06-03", "doi": "10.1016/j.cag.2026.104629", "event": "Spanish Conference on Computer Graphics (CEIG 26)", "issn": "0097-8493", "journal": "Computers & Graphics", "lecturer": [ 5233 ], "location": "Valencia, Spain", "open_access": "yes", "volume": "138", "research_areas": [ "Modeling" ], "keywords": [ "3d point clouds", "physics-based modeling" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "name": "RAOULZADEH-2026-STROKES2DEFORM-image.jpeg", "type": "image/jpeg", "size": 309502, "path": "Publication:RAOULZADEH-2026-STROKES2DEFORM", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/RAOULZADEH-2026-STROKES2DEFORM-image.jpeg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/RAOULZADEH-2026-STROKES2DEFORM-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "RAOULZADEH-2026-STROKES2DEFORM-paper.pdf", "type": "application/pdf", "size": 5302026, "path": "Publication:RAOULZADEH-2026-STROKES2DEFORM", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/RAOULZADEH-2026-STROKES2DEFORM-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/RAOULZADEH-2026-STROKES2DEFORM-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d4314" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RAOULZADEH-2026-STROKES2DEFORM/", "__class": "Publication" }, { "id": "balvan-rsf", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "Reconstruct Sharp Features from Intensity-Derived Scan Angles", "date": "2026-07-23", "abstract": null, "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 928, "image_height": 166, "name": "balvan-rsf-image.png", "type": "image/png", "size": 68928, "path": "Publication:balvan-rsf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/balvan-rsf-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/balvan-rsf-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5382 ], "co_supervisor": [ 948 ], "date_end": "2026-07-23", "date_start": "2024-09-23", "matrikelnr": "12023159", "supervisor": [ 948 ], "research_areas": [ "Geometry" ], "keywords": [ "sharp features", "intensity", "scanning" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 928, "image_height": 166, "name": "balvan-rsf-image.png", "type": "image/png", "size": 68928, "path": "Publication:balvan-rsf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/balvan-rsf-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/balvan-rsf-image:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "balvan-rsf-thesis.pdf", "type": "application/pdf", "size": 20935725, "path": "Publication:balvan-rsf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/balvan-rsf-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/balvan-rsf-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "WorldScale" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/balvan-rsf/", "__class": "Publication" }, { "id": "LIPP-2026-HAIR", "type_id": "journalpaper", "tu_id": null, "repositum_id": null, "title": "High-Performance Real-Time Implicit Strand-Based Hair Rendering via Software Rasterization", "date": "2026-07-01", "abstract": "In this work we propose an efficient deferred software rasterization pipeline for real-time rendering of strand-based hair using hair meshes. Hair plays a crucial role in creating expressive 3D characters, yet strand-based approaches are often restricted to high-end hardware and typically applied to only a small number of hero characters. Hair meshes have proven to be an efficient representation capable of handling a wide variety of groom styles, but existing mesh shader-based implementations still suffer from significant bottlenecks. In this work, we address these limitations with a software rasterization approach that improves performance and compatibility. Our method enables efficient far-field strand-based hair rendering—even at a single sample per pixel—by combining deferred shading with a strand filtering and reconstruction step, while requiring only minimal hardware support. To further enhance scalability, we introduce a level-of-detail (LOD) scheme that adapts hair representation and shading complexity based on viewing distance and screen-space coverage, reducing computational cost further while preserving visual fidelity. To the best of our knowledge, this is the first approach to achieve this combination of efficiency, flexibility, scalability, and broad hardware compatibility.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "name": "LIPP-2026-HAIR-image.png", "type": "image/png", "size": 231260, "path": "Publication:LIPP-2026-HAIR", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/LIPP-2026-HAIR-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/LIPP-2026-HAIR-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1525, 1237, 193, 5612 ], "articleno": "58", "date_from": "2026-05-13", "date_to": "2026-05-15", "doi": "10.1145/3820015", "event": "2026 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games", "issn": "2577-6193", "journal": "Proceedings of the ACM on Computer Graphics and Interactive Techniques", "lecturer": [ 1525 ], "location": "San Francisco, USA", "number": "4", "open_access": "yes", "volume": "9", "research_areas": [ "Rendering" ], "keywords": [ "real-time rendering", "hair rendering", "software rasterization" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "name": "LIPP-2026-HAIR-image.png", "type": "image/png", "size": 231260, "path": "Publication:LIPP-2026-HAIR", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/LIPP-2026-HAIR-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/LIPP-2026-HAIR-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "LIPP-2026-HAIR-paper.pdf", "type": "application/pdf", "size": 15711826, "path": "Publication:LIPP-2026-HAIR", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/LIPP-2026-HAIR-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/LIPP-2026-HAIR-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d4314" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/LIPP-2026-HAIR/", "__class": "Publication" }, { "id": "UNTERGUGGENBERGER-2026-ALOD", "type_id": "journalpaper_notalk", "tu_id": null, "repositum_id": null, "title": "Real-Time Rendering Methods With Adaptive Levels of Detail for Fast Rendering of Parametric Objects on Modern GPUs", "date": "2026-07", "abstract": "Parametric functions are an extremely efficient representation for 3D geometry, capable of compactly modelling highly complex objects. Once specified, parametric 3D objects allow for visualization at arbitrary levels of detail (LOD), at no additional memory cost, limited only by the amount of evaluated samples. However, mapping the sample evaluation to the hardware rendering pipelines of modern graphics processing units (GPUs) is not trivial. In this article, we propose a general method for efficient rendering of parametrically-defined 3D objects on modern hardware architectures. Our method adaptively analyzes, allocates and evaluates parametric function samples to produce high-quality renderings. Geometric precision can be modulated from few pixels down to sub-pixel level, enabling real-time frame rates of several 100 frames per second (FPS) for various parametric functions. We propose a dedicated LOD stage, which outputs patches of similar geometric detail to a subsequent rendering stage that uses either a hardware tessellation-based approach or performs point-based software rasterization. Our method requires neither preprocessing nor caching, and the proposed LOD mechanism is fast enough to run each frame. Hence, our approach also lends itself to animated parametric objects. We demonstrate the benefits of our method over a state-of-the-art spherical harmonics (SH) glyph rendering method and over classical LOD approaches, while showing its flexibility on a range of other demanding shapes.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "name": "UNTERGUGGENBERGER-2026-ALOD-image.png", "type": "image/png", "size": 164187, "path": "Publication:UNTERGUGGENBERGER-2026-ALOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/UNTERGUGGENBERGER-2026-ALOD-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/UNTERGUGGENBERGER-2026-ALOD-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 848, 1525, 193, 1662, 1650, 1116 ], "doi": "10.1109/TVCG.2025.3638697", "journal": "IEEE Transactions on Visualization and Computer Graphics", "number": "7", "open_access": "yes", "pages_from": "4931", "pages_to": "4944", "volume": "32", "research_areas": [ "Rendering" ], "keywords": [ "real-time rendering", "parametric rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "name": "UNTERGUGGENBERGER-2026-ALOD-image.png", "type": "image/png", "size": 164187, "path": "Publication:UNTERGUGGENBERGER-2026-ALOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/UNTERGUGGENBERGER-2026-ALOD-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/UNTERGUGGENBERGER-2026-ALOD-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "UNTERGUGGENBERGER-2026-ALOD-paper.pdf", "type": "application/pdf", "size": 5297649, "path": "Publication:UNTERGUGGENBERGER-2026-ALOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/UNTERGUGGENBERGER-2026-ALOD-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/UNTERGUGGENBERGER-2026-ALOD-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/UNTERGUGGENBERGER-2026-ALOD/", "__class": "Publication" }, { "id": "SCHUETZ-2026-CURAST", "type_id": "journalpaper", "tu_id": null, "repositum_id": null, "title": "CuRast: Cuda-Based Software Rasterization for Billions of Triangles", "date": "2026-07", "abstract": "This paper presents a CUDA-based software rasterizer capable of rendering up to a billion unique triangles, or up to 4 billion instanced triangles, in real time at 60 fps on an RTX 5090. By specifically targeting dense, opaque meshes, our approach is able to outperform the native GPU rasterization pipeline in these scenarios. The resulting performance enables rapid loading and visualization of massive triangle datasets without requiring precomputed spatial acceleration or level-of-detail structures, and supports applications such as efficient editing of large-scale geometry. While the method is primarily designed for dense meshes that generate pixel-sized triangles, we additionally introduce a three-stage pipeline to handle larger primitives. The source code is available at: https://github.com/m-schuetz/CuRast", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 439, "image_height": 246, "name": "SCHUETZ-2026-CURAST-image.png", "type": "image/png", "size": 82967, "path": "Publication:SCHUETZ-2026-CURAST", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/SCHUETZ-2026-CURAST-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/SCHUETZ-2026-CURAST-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 1525, 1935, 193 ], "articleno": "e70538", "date_from": "2026-07-01", "date_to": "2026-07-03", "doi": "10.1111/cgf.70538", "event": "Eurographics Symposium on Rendering 2026", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1116 ], "location": "Bordeaux, France", "number": "4", "volume": "45", "research_areas": [ "IllVis" ], "keywords": [ "real-time rendering", "software rasterization" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 439, "image_height": 246, "name": "SCHUETZ-2026-CURAST-image.png", "type": "image/png", "size": 82967, "path": "Publication:SCHUETZ-2026-CURAST", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/SCHUETZ-2026-CURAST-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/SCHUETZ-2026-CURAST-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2026-CURAST-paper.pdf", "type": "application/pdf", "size": 17283939, "path": "Publication:SCHUETZ-2026-CURAST", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/SCHUETZ-2026-CURAST-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/SCHUETZ-2026-CURAST-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d9275", "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/SCHUETZ-2026-CURAST/", "__class": "Publication" }, { "id": "RASOULZADEH-2026-PREDICTING", "type_id": "inproceedings", "tu_id": null, "repositum_id": null, "title": "Predicting Deformation Fields on 3D Stroke Clouds", "date": "2026-07", "abstract": "Deformation analysis is typically performed only after geometric modeling in design workflows, depriving designers of this physical insight during the early sketching phase, when the design has the highest optimization potential. To bridge this gap, we propose a physics-informed neural model that takes as input a 3D sketch stroke cloud and user-specified boundary conditions, and directly predicts the induced 3D deformation field on the stroke cloud without requiring reconstruction-and-simulation. To represent unstructured 3D sketches and user-annotated boundary conditions in a form suitable for learning, we use fVDB to encode stroke clouds into sparse voxel grids and leverage its differentiable splatting and sampling operators for bidirectional point–voxel mappings. Trained on our synthetic dataset of architectural thin-shell sketch–deformation pairs, our dual-head model predicts per-point displacement magnitudes and unit-length vectors, and is optimized using physics-informed loss terms inspired by stretching and bending as the two modes of deformation.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 478, "image_height": 314, "name": "RASOULZADEH-2026-PREDICTING-image.png", "type": "image/png", "size": 185079, "path": "Publication:RASOULZADEH-2026-PREDICTING", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/RASOULZADEH-2026-PREDICTING-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/RASOULZADEH-2026-PREDICTING-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5233, 5613, 5614, 1799, 193 ], "articleno": "ceig.20261012", "booktitle": "Spanisch Computer Graphics Conference Short Papers", "date_from": "2026-06-01", "date_to": "2026-06-03", "doi": "10.2312/ceig.20261012", "event": "Spanish Conference on Computer Graphics (CEIG 26)", "isbn": "978-3-03868-301-8", "lecturer": [ 5233 ], "open_access": "yes", "series": "Eurographics", "research_areas": [ "Modeling" ], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 478, "image_height": 314, "name": "RASOULZADEH-2026-PREDICTING-image.png", "type": "image/png", "size": 185079, "path": "Publication:RASOULZADEH-2026-PREDICTING", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/RASOULZADEH-2026-PREDICTING-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/RASOULZADEH-2026-PREDICTING-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "RASOULZADEH-2026-PREDICTING-paper.pdf", "type": "application/pdf", "size": 5558934, "path": "Publication:RASOULZADEH-2026-PREDICTING", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/RASOULZADEH-2026-PREDICTING-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/RASOULZADEH-2026-PREDICTING-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d4314" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/RASOULZADEH-2026-PREDICTING/", "__class": "Publication" }, { "id": "lehmann-2026-label", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "Automatic Edge Label Prediction for a Graph-Based Image Generation Interface", "date": "2026-06-30", "abstract": "The majority of text-to-image generation systems rely on linear text prompts, which struggle to represent complex relationships. Building upon an existing prompting tree interface for image generation which allows the description of prompts using nodes and edges, this research investigates the enhancement of graph-based prompting through two contributions: automated edge-label generation optimized graph visualization. By providing upgrades to the system, users can create graphs with an integrated Large Language Model (Qwen) or Masked Language Model (BERT) to automatically generate edge labels in the prompting tree. Furthermore, we introduce a secondary \"overview layout\" using the Dagre engine to address graph readability and label occlusion.\nThe evaluation focuses on three aspects: the accuracy and efficiency of automated edgelabel generation, its impact on image quality as measured by CLIP scores, and the effectiveness of the overview layout for graph visualization. Experiments demonstrate that BERT has faster inference times compared to Qwen and generates more reliable predictions. Although the impact of augmented prompts on final image quality varied, the proposed overview layout successfully optimized the distribution of graph elements and eliminated label occlusion.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1532, "image_height": 1839, "name": "lehmann-2026-label-teaser.png", "type": "image/png", "size": 257274, "path": "Publication:lehmann-2026-label", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/lehmann-2026-label-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/lehmann-2026-label-teaser:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5602 ], "date_end": "2026-06", "date_start": "2025-12", "matrikelnr": "12225096", "supervisor": [ 1653 ], "research_areas": [ "InfoVis" ], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1532, "image_height": 1839, "name": "lehmann-2026-label-teaser.png", "type": "image/png", "size": 257274, "path": "Publication:lehmann-2026-label", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/lehmann-2026-label-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/lehmann-2026-label-teaser:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "lehmann-2026-label-thesis.pdf", "type": "application/pdf", "size": 2608314, "path": "Publication:lehmann-2026-label", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/lehmann-2026-label-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/lehmann-2026-label-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "d9282" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/lehmann-2026-label/", "__class": "Publication" }, { "id": "di_bartolomeo-2026-tss", "type_id": "inproceedings", "tu_id": null, "repositum_id": "20.500.12708/229110", "title": "The Story(line) So Far: A Survey on Storyline Visualization", "date": "2026-06-08", "abstract": "Storyline visualizations model narratives as temporal networks, using x-monotone lines to represent entities and their interactions over time. This technique offers an intuitive way to reveal structural patterns over time, such as character co-occurrence and narrative flow. Storylines represent a visualization approach with growing interest from the visualization community and applications in diverse contexts. Researchers have developed various layout algorithms and formalized a set of optimization objectives with the goal of automating their generation and balancing their readability, graph aesthetics, and efficiency. These methods vary in their algorithmic formulations and implementations as well as the visual elements they support, such as labels, grouping, or continuity preservation across time. This state-of-the-art report maps the current landscape of storyline visualization approaches, with a specific focus on the visual structures, optimization objectives, and the characteristic of the layout algorithms that generate these.", "authors_et_al": false, "substitute": null, "main_image": { "description": "A storyline of publications included in this survey over time. Colored dots represent individual papers (“events”). Lines\ncorrespond to institutions that appear in more than one publication, while papers from other institutions are shown as isolated dots.\nCollaborations between institutions are indicated by blue rectangles. The visualization highlights a vibrant research field, with recurring\ncollaborations and a steady stream of publications across years. Note that, in this case in particular, the graph is laid out manually.", "filetitle": "teaser", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 3573, "image_height": 1772, "name": "di_bartolomeo-2026-tss-teaser.png", "type": "image/png", "size": 314868, "path": "Publication:di_bartolomeo-2026-tss", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/di_bartolomeo-2026-tss-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/di_bartolomeo-2026-tss-teaser:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5488, 5605, 5417, 1579, 1850 ], "booktitle": "EuroVis 2026: 28th Eurographics Conference on Visualization 2026", "date_from": "2026-06-08", "date_to": "2026-06-12", "doi": "10.1111/cgf.70499", "editor": "Abdul-Rahman, Alfie and Angelini, Marco and Preim, Bernhard", "event": "28th Eurographics Conference on Visualization (EuroVis 2026)", "lecturer": [ 5488 ], "location": "Nottingham", "open_access": "yes", "pages": "30", "volume": "45/3", "research_areas": [], "keywords": [ "Storyline Visualization", "Dynamic Networks", "Visualization", "Visual Analytics", "Graph Drawing" ], "weblinks": [], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "di_bartolomeo-2026-tss-paper.pdf", "type": "application/pdf", "size": 1659099, "path": "Publication:di_bartolomeo-2026-tss", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/di_bartolomeo-2026-tss-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/di_bartolomeo-2026-tss-paper:thumb{{size}}.png" }, { "description": "A storyline of publications included in this survey over time. Colored dots represent individual papers (“events”). Lines\ncorrespond to institutions that appear in more than one publication, while papers from other institutions are shown as isolated dots.\nCollaborations between institutions are indicated by blue rectangles. The visualization highlights a vibrant research field, with recurring\ncollaborations and a steady stream of publications across years. Note that, in this case in particular, the graph is laid out manually.", "filetitle": "teaser", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 3573, "image_height": 1772, "name": "di_bartolomeo-2026-tss-teaser.png", "type": "image/png", "size": 314868, "path": "Publication:di_bartolomeo-2026-tss", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/di_bartolomeo-2026-tss-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/di_bartolomeo-2026-tss-teaser:thumb{{size}}.png" } ], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/di_bartolomeo-2026-tss/", "__class": "Publication" }, { "id": "eschner-2026-fpa", "type_id": "inproceedings", "tu_id": null, "repositum_id": "20.500.12708/229185", "title": "Fishing for Papers: A Serendipitous Knowledge Discovery Game", "date": "2026-06-08", "abstract": "Fishing has long been used as a metaphor for information-seeking. In the context of literature research, we may see a query act as bait, with the researcher observing what papers “bite”. Taking this analogy literally, we created an open-ended fishing game for literature exploration. Our game aims to support serendipitous knowledge discovery in a playful, relaxing way. In our game, the player uses a virtual bait, the Keyworm (a set of keywords), to catch papers from a Pond (the paper pool for a given venue). To engage players in serendipitous discovery, we introduce a serendipity measurement that categorizes papers into varying levels of rarity. Players are encouraged to iteratively experiment with different keywords to navigate the paper corpus and catch unexpectedly interesting papers. Our game employs the cozy game design principles to provide a relaxing and enjoyable way for visualization researchers to explore the visualization literature. We evaluated the game in playtests with six researchers and made it available as an online demo: https://fishing-for-papers.github.io/game/.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 3006, "image_height": 1180, "name": "eschner-2026-fpa-teaser.png", "type": "image/png", "size": 1057730, "path": "Publication:eschner-2026-fpa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/eschner-2026-fpa-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/eschner-2026-fpa-teaser:thumb{{size}}.png" }, "sync_repositum_override": "date", "repositum_presentation_id": null, "authors": [ 1653, 5610 ], "booktitle": "VisGames 2026: EuroVis Workshop on Visualization Play, Games, and Activities", "date_from": "2026-06-08", "date_to": "2026-06-12", "doi": "10.2312/visgames.20261002", "editor": "Fellner, Dieter", "event": "EuroVis 2026 - 28th EG Conference on Visualization", "isbn": "978-3-03868-307-0", "lecturer": [ 1653 ], "location": "Nottingham", "open_access": "yes", "pages": "6", "publisher": "The Eurographics Association", "research_areas": [ "InfoVis" ], "keywords": [ "Human-centered computing", "Visualization", "Computer games", "Information Retrieval", "Applied computing", "Information Systems" ], "weblinks": [], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "eschner-2026-fpa-paper.pdf", "type": "application/pdf", "size": 5149202, "path": "Publication:eschner-2026-fpa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/eschner-2026-fpa-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/eschner-2026-fpa-paper:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 3006, "image_height": 1180, "name": "eschner-2026-fpa-teaser.png", "type": "image/png", "size": 1057730, "path": "Publication:eschner-2026-fpa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/eschner-2026-fpa-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/eschner-2026-fpa-teaser:thumb{{size}}.png" } ], "projects_workgroups": [ "d9282" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/eschner-2026-fpa/", "__class": "Publication" }, { "id": "ulschmid-2026-naadf", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/228306", "title": "NAADF: Globally Illuminated Voxel Worlds Accelerated with Nested Axis‐Aligned Distance Fields", "date": "2026-05", "abstract": "Achieving realistic rendering of 3D scenes in real time using path tracing is challenging due to the high sample count required, with ray tracing as the bottleneck. Focusing on voxels as a geometry representation offers significant opportunities for optimizations, especially for tracing the rays, but also for computing the samples. We propose a novel multilayered spatial structure augmented with in-cell axis-aligned distance fields (AADF) operating as caches. Our nested cell structure already accelerates ray tracing 3-5x compared to the state-of-the-art dense spatial structures, such as variants of directed acyclic graphs (DAG). Using the AADFs (constructed while rendering) inside the cells, we can double the ray throughput again (total 10x). As an application, exploiting nested AADFs (NAADFs) also allows us to double the speed of global illumination computations while significantly reducing artifacts from camera motion, such as flickering, blurring, ghosting, and aliasing, all of which are especially important in voxel worlds with sharp edges. We achieve this by adapting temporal antialiasing (TAA) to retain the last 32 frames rather than a single history buffer to create the final antialiased image, since the discretized voxel structure requires much less memory to store the quantized positions and normals of ray bounces. The sample accumulation for global illumination is optimized by compressing and separating lit/unlit samples, and we apply 8x8 window spatial resampling based on a reservoir-based spatiotemporal importance resampling (ReSTIR) method. Our proposed NAADFs support editing with quick updates to the acceleration in the background, overlays of non-aligned dynamic geometry, and can be easily extended to support transform-aware compression or to represent huge real-world scans. Retaining many past frames rather than just combining them opens up new opportunities to remove spatial and temporal artifacts in path tracing for global illumination.", "authors_et_al": false, "substitute": null, "main_image": { "description": "Rendering of a large voxel world", "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 3840, "image_height": 2160, "name": "ulschmid-2026-naadf-image.png", "type": "image/png", "size": 15419290, "path": "Publication:ulschmid-2026-naadf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-image:thumb{{size}}.png" }, "sync_repositum_override": "articleno,date_from,date_to,event,lecturer,number,volume", "repositum_presentation_id": null, "authors": [ 1954, 5599, 5600, 193, 948 ], "articleno": "53", "date_from": "2026-05", "date_to": "2026-05", "doi": "10.1111/cgf.70413", "event": "Eurographics 2026", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1954 ], "number": "2", "open_access": "yes", "pages": "14", "publisher": "WILEY", "volume": "45", "research_areas": [ "Rendering" ], "keywords": [ "CCS Concepts", "Volumetric models", "Computing methodologies → Ray tracing", "Voxel Worlds", "Rendering", "Distance Fields", "Global Illumination" ], "weblinks": [ { "href": "https://github.com/cg-tuwien/NAADF", "caption": "GitHub", "description": null, "main_file": 1 } ], "files": [ { "description": "Rendering of a large voxel world", "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 3840, "image_height": 2160, "name": "ulschmid-2026-naadf-image.png", "type": "image/png", "size": 15419290, "path": "Publication:ulschmid-2026-naadf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "ulschmid-2026-naadf-paper.pdf", "type": "application/pdf", "size": 48766998, "path": "Publication:ulschmid-2026-naadf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-paper:thumb{{size}}.png" }, { "description": "Comparison of ReSTIR and TAA algorithms", "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 556, "image_height": 555, "name": "ulschmid-2026-naadf-teaser.png", "type": "image/png", "size": 640679, "path": "Publication:ulschmid-2026-naadf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-teaser:thumb{{size}}.png" }, { "description": "Showcase of NAADFs, entites and editing", "filetitle": "video 1", "main_file": false, "use_in_gallery": false, "access": "public", "name": "ulschmid-2026-naadf-video 1.mp4", "type": "video/mp4", "size": 521421869, "path": "Publication:ulschmid-2026-naadf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-video 1.mp4", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-video 1:thumb{{size}}.png", "video_mp4": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-video 1:video.mp4" }, { "description": "Rendering showcase", "filetitle": "video 2", "main_file": false, "use_in_gallery": false, "access": "public", "name": "ulschmid-2026-naadf-video 2.mp4", "type": "video/mp4", "size": 475380361, "path": "Publication:ulschmid-2026-naadf", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-video 2.mp4", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-video 2:thumb{{size}}.png", "video_mp4": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/ulschmid-2026-naadf-video 2:video.mp4" } ], "projects_workgroups": [ "WorldScale", "d4314" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/ulschmid-2026-naadf/", "__class": "Publication" }, { "id": "kristmann-2026-vtc", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/228442", "title": "Variable‐Rate Texture Compression: Real‐Time Rendering with JPEG", "date": "2026-05", "abstract": "Although variable-rate compressed image formats such as JPEG are widely used to efficiently encode images, they have not found their way into real-time rendering due to special requirements such as random access to individual texels. In this paper, we investigate the feasibility of variable-rate texture compression on modern GPUs using the JPEG format, and how it compares to the GPU-friendly fixed-rate compression approaches BC1 and ASTC. Using a deferred rendering pipeline, we are able to identify the subset of blocks that are needed for a given frame, decode these, and colorize the framebuffer's pixels. Despite the additional ∼0.17 bit per pixel that we require for our approach, JPEG maintains significantly better quality and compression rates compared to BC1, and depending on the type of image, outperforms or competes with ASTC. The JPEG rendering pipeline increases rendering duration by less than 0.3 ms on an NVIDIA RTX 4090, demonstrating that sophisticated variable-rate compression schemes are feasible on modern GPUs, even in VR. Source code and data sets are available at: https://github.com/elias1518693/jpeg_textures.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1128, "image_height": 592, "name": "kristmann-2026-vtc-image.png", "type": "image/png", "size": 1480794, "path": "Publication:kristmann-2026-vtc", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/kristmann-2026-vtc-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/kristmann-2026-vtc-image:thumb{{size}}.png" }, "sync_repositum_override": "date,projects,articleno,date_from,date_to,doi,event,lecturer,location,number,volume", "repositum_presentation_id": null, "authors": [ 1935, 193, 1116 ], "articleno": "e70338", "date_from": "2026-05-04", "date_to": "2026-05-08", "doi": "10.1111/cgf.70338", "event": "Eurographics 2026", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1935 ], "location": "Aachen, Germany", "number": "2", "open_access": "yes", "pages": "13", "publisher": "WILEY", "volume": "45", "research_areas": [ "Rendering" ], "keywords": [ "CCS Concepts", "Image compression", "Computing methodologies", "real-time rendering", "texture compression" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1128, "image_height": 592, "name": "kristmann-2026-vtc-image.png", "type": "image/png", "size": 1480794, "path": "Publication:kristmann-2026-vtc", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/kristmann-2026-vtc-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/kristmann-2026-vtc-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "kristmann-2026-vtc-paper.pdf", "type": "application/pdf", "size": 18926678, "path": "Publication:kristmann-2026-vtc", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/kristmann-2026-vtc-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/kristmann-2026-vtc-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d9275", "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kristmann-2026-vtc/", "__class": "Publication" }, { "id": "grammatikaki-2026-rootscape", "type_id": "poster", "tu_id": null, "repositum_id": "20.500.12708/229436", "title": "RootScape: Visual Analytics for Subsurface-Aware Urban Tree Planning", "date": "2026-04-27", "abstract": "We present RootScape, a browser-based visual analytics system fusing eight open geospatial datasets for Vienna into a depth-coherent 3D scene from tree crown to tunnel. Four coordinated views support the full planning workflow: a 3D Mapping environment with user-controlled temporal simulation of root-halo and crown growth, a Cross-Section view revealing subsurface geometry at true depth, a Viability Planner scoring eight species against ten substrate constraints with per-factor breakdown and conflict-year prediction, and a District Analytics view for strategic stress assessment. Retrospective validation against the Vienna Baumkataster surfaces 81 unexplained high-stress trees in our study area as inspection candidates and produces zero false high-risk alarms. RootScape is the first system to expose the invisible subsurface conflict between urban greenery and gray infrastructure in an interactive, open-data, planning-oriented context. The codebase and demo are publicly available at https://github.com/AngelikiGram/rootscape.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 4700, "image_height": 2198, "name": "grammatikaki-2026-rootscape-teaser.png", "type": "image/png", "size": 7859242, "path": "Publication:grammatikaki-2026-rootscape", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-teaser:thumb{{size}}.png" }, "sync_repositum_override": "authors,date", "repositum_presentation_id": null, "authors": [ 1937, 5485, 1110 ], "booktitle": "EuroVis 2026 : 28th Eurographics Conference on Visualization 2026 : Posters", "cfp": { "name": "call_for_papers_eurovis_posters.pdf", "type": "application/pdf", "error": 0, "size": 1161902, "orig_name": "call_for_papers_eurovis_posters.pdf", "ext": "pdf" }, "date_from": "2026-06-08", "date_to": "2026-06-12", "doi": "10.2312/evpd.20261025", "editor": "Elshealhy, Mai and Furmanova, Katarina and Garrison, Laura and Médoc, Nicolas", "event": "28th Eurographics Conference on Visualization (EuroVis 2026)", "isbn": "978-3-03868-305-6", "lecturer": [ 1937 ], "location": "Nottingham", "open_access": "yes", "pages": "3", "publisher": "The Eurographics Association", "research_areas": [], "keywords": [ "Visual analytics", "Geographic visualization", "Rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "grammatikaki-2026-rootscape-paper.pdf", "type": "application/pdf", "size": 2947037, "path": "Publication:grammatikaki-2026-rootscape", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-paper:thumb{{size}}.png" }, { "description": null, "filetitle": "poster", "main_file": false, "use_in_gallery": false, "access": "public", "name": "grammatikaki-2026-rootscape-poster.pdf", "type": "application/pdf", "size": 7624224, "path": "Publication:grammatikaki-2026-rootscape", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-poster.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-poster:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 4700, "image_height": 2198, "name": "grammatikaki-2026-rootscape-teaser.png", "type": "image/png", "size": 7859242, "path": "Publication:grammatikaki-2026-rootscape", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/grammatikaki-2026-rootscape-teaser:thumb{{size}}.png" } ], "projects_workgroups": [ "d10164" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-rootscape/", "__class": "Publication" }, { "id": "grammatikaki-2026-treesformer", "type_id": "inproceedings", "tu_id": null, "repositum_id": "20.500.12708/229409", "title": "TreesFormer: Multimodal Grammar-Based 3D Tree Reconstruction from Sparse Geodata", "date": "2026-04-24", "abstract": "We present TreesFormer, the first grammar-based framework for reconstructing hierarchical 3D tree structures directly from sparse top-down geodata using only a single orthophoto and its corresponding Digital Surface Model (DSM). It employs a multi-modal autoregressive transformer that predicts compact parametric L-system grammars from DSM point clouds and orthophoto features, jointly predicting symbolic structure and geometric parameters while enforcing grammar constraints during decoding. To enable supervision in the absence of real-world grammar annotations, we introduce a synthetic multimodal dataset of procedurally generated trees with aligned aerial inputs and ground-truth L-system labels. Experiments show that DSMs drive overall geometric accuracy and crown shape, while orthophoto conditioning improves structural regularity and branching depth; their combination consistently outperforms either modality alone. The model generalizes to real-world Austrian and French aerial data, producing interpretable branching structures suitable for large-scale rural 3D mapping. The codebase, synthetic dataset, and pretrained model are publicly available at https://angelikigram.github.io/treesformer/.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 2800, "image_height": 1042, "name": "grammatikaki-2026-treesformer-teaser.png", "type": "image/png", "size": 1993656, "path": "Publication:grammatikaki-2026-treesformer", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/grammatikaki-2026-treesformer-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/grammatikaki-2026-treesformer-teaser:thumb{{size}}.png" }, "sync_repositum_override": "date,pages_from,pages_to", "repositum_presentation_id": null, "authors": [ 1937, 5485, 1110 ], "booktitle": "Computer Graphics & Visual Computing (CGVC) 2026", "date_from": "2026-06-08", "date_to": "2026-06-12", "doi": "10.2312/cgvc.20261008", "editor": "Sheng, Yun and Elshehaly, Mai", "event": "28th Eurographics Conference on Visualization (EuroVis 2026)", "isbn": "978-3-03868-319-3", "lecturer": [ 1937 ], "location": "Nottingham", "open_access": "yes", "pages": "10", "pages_from": "1", "pages_to": "10", "publisher": "The Eurographics Association", "research_areas": [], "keywords": [ "Neural networks", "Mesh models", "Reconstruction" ], "weblinks": [], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "grammatikaki-2026-treesformer-paper.pdf", "type": "application/pdf", "size": 21512091, "path": "Publication:grammatikaki-2026-treesformer", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/grammatikaki-2026-treesformer-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/grammatikaki-2026-treesformer-paper:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 2800, "image_height": 1042, "name": "grammatikaki-2026-treesformer-teaser.png", "type": "image/png", "size": 1993656, "path": "Publication:grammatikaki-2026-treesformer", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/grammatikaki-2026-treesformer-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/grammatikaki-2026-treesformer-teaser:thumb{{size}}.png" } ], "projects_workgroups": [ "d10164", "VRVis" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treesformer/", "__class": "Publication" }, { "id": "rozana-2026-vcfd", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "Visual Composition and Exploration of Financial Dataflows", "date": "2026-04", "abstract": "This thesis investigates how interactive visualization techniques can improve transparency\nin node-based editors for financial time-series data. Existing tools in this domain\nsupport workflow construction but provide limited means for inspecting intermediate\nvalues or tracing dataflow through a processing pipeline. Following a Data–Users–\nTasks design triangle, the work derives seven design requirements from the literature\nand implements them in a web-based node-based editor. The system provides nodelevel\nprobes for intermediate-state inspection, coordinated graph and chart views with\ncolor-coded linking, execution-based dataflow highlighting, and integrated backtesting\nvisualization. A case study using a moving average crossover workflow demonstrates\nthe system in operation. The results show that for static, fully visible time-series data,\ntemporal scrubbing provides no benefit over direct crosshair navigation, contrasting\nwith reactive visualization systems where timeline replay is necessary. Persistent color\nencoding replaces interactive brushing-and-linking, and user-controlled layout flexibility\nsupports both superposition and juxtaposition depending on the inspection task.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5586 ], "date_end": "2026-04", "date_start": "2025-08", "matrikelnr": "12024732", "supervisor": [ 1110 ], "research_areas": [ "InfoVis" ], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "rozana-2026-vcfd-thesis.pdf", "type": "application/pdf", "size": 2278889, "path": "Publication:rozana-2026-vcfd", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/rozana-2026-vcfd/rozana-2026-vcfd-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/rozana-2026-vcfd/rozana-2026-vcfd-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "vis" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/rozana-2026-vcfd/", "__class": "Publication" }, { "id": "muth-2026-clouds", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "Real-Time Volumetric Rendering of Meteorological Cloud Data", "date": "2026-03-25", "abstract": "Traditional meteorological visualizations collapse the vertical structure of the atmosphere\ninto two-dimensional map overlays, losing precisely the information most relevant in\ncomplex terrain. Expert tools for three-dimensional atmospheric exploration exist, but\ntarget domain scientists on dedicated workstation infrastructure. This thesis presents a\npipeline for the real-time volumetric rendering of meteorological cloud data within the\nweBIGeo web-based geographic visualization platform, with the goal of making cloud\nstructure intuitively readable to general users in a standard web browser.\nThe pipeline transforms hourly ICON-D2 forecast output into a compressed, streamable\ntile hierarchy that a WebGPU ray-marcher samples at interactive frame rates. Preprocessing\na single forecast timestamp completes in approximately 33 s of compute time,\nproducing a tile hierarchy of roughly 86MiB on average. Rendering cost is well within\ninteractive bounds: even under high cloud coverage, the cloud pass consumes around\n2.25ms of GPU time, a small fraction of the 33ms budget for 30 fps. Qualitative evaluation\nagainst EUMETSAT satellite imagery shows that large-scale cloud patterns are\nreproduced with reasonable fidelity. Comparison against webcam imagery reveals three\nconcrete limitations: the coarse and non-uniform vertical resolution of the source data\nis insufficient to resolve sharp fog layer boundaries, the sub-grid density distribution\ndoes not preserve the character of small cloud elements such as wispy puffs, and the tile\nresolution is too coarse to encode the surface texture of individual cumulus cells. The\nsystem is best understood as a large-scale atmospheric context layer rather than a precise\nlocal forecast tool.", "authors_et_al": false, "substitute": null, "main_image": { "description": "clouds in weBIGeo", "filetitle": "teaser", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1958, "image_height": 1159, "name": "muth-2026-clouds-teaser.png", "type": "image/png", "size": 4142519, "path": "Publication:muth-2026-clouds", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-teaser:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5585 ], "date_end": "2026-03", "date_start": "2025-10", "matrikelnr": "12226614", "supervisor": [ 1110 ], "research_areas": [ "Rendering" ], "keywords": [], "weblinks": [ { "href": "https://github.com/Qendolin/webigeo-clouds", "caption": "GitHub Cloud Renderer", "description": null, "main_file": 0 }, { "href": "https://github.com/Qendolin/webigeo-clouds-server", "caption": "GitHub Cloud Preprocessing Server", "description": null, "main_file": 0 } ], "files": [ { "description": "clouds in weBIGeo", "filetitle": "teaser", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1958, "image_height": 1159, "name": "muth-2026-clouds-teaser.png", "type": "image/png", "size": 4142519, "path": "Publication:muth-2026-clouds", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-teaser:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "muth-2026-clouds-thesis.pdf", "type": "application/pdf", "size": 20583815, "path": "Publication:muth-2026-clouds", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-thesis:thumb{{size}}.png" }, { "description": "Short video sequence zooming into a cloudy scene", "filetitle": "video", "main_file": false, "use_in_gallery": false, "access": "public", "name": "muth-2026-clouds-video.mp4", "type": "video/mp4", "size": 8692035, "path": "Publication:muth-2026-clouds", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-video.mp4", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-video:thumb{{size}}.png", "video_mp4": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/muth-2026-clouds-video:video.mp4" } ], "projects_workgroups": [ "d9555" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/muth-2026-clouds/", "__class": "Publication" }, { "id": "slajcho_levente-baa", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "CycleSafely - record depth images", "date": "2026-03-23", "abstract": "Tasks:\n- mount the devices by stativ interface (OAK-D, Insta 360 X2 ONE, Smartphone) on bicycle (helmet and handlebar) - possibly 3d print, ideally something low-threshold that everyone can easily construct\n- connect powerbank (<3mAh per hour, since 3A/5V) by cutting/connecting cables or finding a suitable adapter\n- oak-d: usb cable to smartphone, transfer point clouds to smartphone (SDK? python)\n- transfer photos from insta 360 to smartphone and de-fish eye it (get code from Aleks)\n- estimate depth from photo (for insta 360 and smartphone) - can maybe use the network from the camera (or camera directly)\n- client/server transfer (get code from Aleks) of point clouds to server (where pipeline of simon takes over the rest)\n\n\n", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 480, "image_height": 205, "name": "slajcho_levente-baa-image.png", "type": "image/png", "size": 173043, "path": "Publication:slajcho_levente-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/slajcho_levente-baa-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/slajcho_levente-baa-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5352 ], "date_end": "2026-03-23", "date_start": "2024-12-04", "matrikelnr": "01634250", "supervisor": [ 948 ], "research_areas": [ "Geometry" ], "keywords": [ "bicycle", "scanning", "client-server" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 480, "image_height": 205, "name": "slajcho_levente-baa-image.png", "type": "image/png", "size": 173043, "path": "Publication:slajcho_levente-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/slajcho_levente-baa-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/slajcho_levente-baa-image:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "slajcho_levente-baa-thesis.pdf", "type": "application/pdf", "size": 5412897, "path": "Publication:slajcho_levente-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/slajcho_levente-baa-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/slajcho_levente-baa-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "WorldScale" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/slajcho_levente-baa/", "__class": "Publication" }, { "id": "bayer_bernhard-2026-baa", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "CycleSafely Mobile", "date": "2026-03-21", "abstract": null, "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 466, "image_height": 274, "name": "bayer_bernhard-2026-baa-image.png", "type": "image/png", "size": 98770, "path": "Publication:bayer_bernhard-2026-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/bayer_bernhard-2026-baa-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/bayer_bernhard-2026-baa-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5596 ], "co_supervisor": [ 948 ], "date_end": "2026-03-21", "date_start": "2024-10-29", "matrikelnr": "01228892", "supervisor": [ 193 ], "research_areas": [ "Geometry" ], "keywords": [ "mobile", "object detection", "cycling" ], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 466, "image_height": 274, "name": "bayer_bernhard-2026-baa-image.png", "type": "image/png", "size": 98770, "path": "Publication:bayer_bernhard-2026-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/bayer_bernhard-2026-baa-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/bayer_bernhard-2026-baa-image:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "bayer_bernhard-2026-baa-thesis.pdf", "type": "application/pdf", "size": 1906293, "path": "Publication:bayer_bernhard-2026-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/bayer_bernhard-2026-baa-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/bayer_bernhard-2026-baa-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "WorldScale" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/bayer_bernhard-2026-baa/", "__class": "Publication" }, { "id": "Musleh_PhD", "type_id": "phdthesis", "tu_id": null, "repositum_id": "20.500.12708/224040", "title": "Guided Visual Analytics for Decision Making under Uncertainty", "date": "2026-03", "abstract": "Visual Analytics (VA) has emerged from the need to optimize decision making by involving human reasoning in sense making. The development of VA has been facilitated by significant technological advances in modern computer graphics and data processing capabilities. Involving humans in the loop aims to address high-risk scenarios where artificial intelligence (AI) automated approaches are insufficient. One active area of research with VA is the development of methods that enable the user to make efficient and effective decisions under high uncertainty. Yet, the field of VA research has not fully understood how user attitude, namely trust and confidence, interplay in VA decision making under uncertainty. Properties of the user attitude play a crucial role in optimizing VA decision making, but they are challenging to externalize and evaluate. For instance, user confidence in their decision emerges as an important indicator of effectiveness when the correctness of the decision cannot be measured. In this dissertation, we explore the use of guidance techniques to address uncertainties in VA decision making, focusing on scenarios where the correctness of decisions cannot be definitively established. Throughout this work, we learned that a multidimensional guidance mechanism can address uncertainties more effectively when uncertainties are challenging to quantify and visualize, especially in the case of subjective uncertainty. However, evaluating the effectiveness of guidance approaches requires a more comprehensive analysis of the interplay between trust and confidence within the sense-making process. Using provenance networks and SNA metrics can provide a more reliable and comprehensive assessment of user confidence, indicating that such approaches can be employed to support co-adaptive guidance.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": "title,abstract,date,keywords", "repositum_presentation_id": null, "authors": [ 1867 ], "ac_number": "AC17745765", "date_end": "2025", "date_start": "2021", "doi": "10.34726/hss.2026.137814", "open_access": "yes", "pages": "185", "reviewer_1": [ 5252 ], "reviewer_2": [ 5243 ], "rigorosum": "2025-11", "supervisor": [ 1410 ], "research_areas": [ "InfoVis", "MedVis" ], "keywords": [ "Visualization", "Visual Analytics", "Guidance", "Trust", "Confidence" ], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "Musleh_PhD-thesis.pdf", "type": "application/pdf", "size": 6169556, "path": "Publication:Musleh_PhD", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/Musleh_PhD/Musleh_PhD-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/Musleh_PhD/Musleh_PhD-thesis:thumb{{size}}.png" } ], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/Musleh_PhD/", "__class": "Publication" }, { "id": "kovacs-2026-sbg", "type_id": "journalpaper_notalk", "tu_id": null, "repositum_id": "20.500.12708/226679", "title": "Style Brush: Guided Style Transfer for 3D Objects", "date": "2026-02-16", "abstract": "We introduce Style Brush, a novel style transfer method for textured meshes designed to empower artists with fine-grained control over the stylization process. Our approach extends traditional 3D style transfer methods by introducing a novel loss function that captures style directionality, supports multiple style images or portions thereof and enables smooth transitions between styles in the synthesized texture. The use of easily generated guiding textures streamlines user interaction, making our approach accessible to a broad audience. Extensive evaluations with various meshes, style images and contour shapes demonstrate the flexibility of our method and showcase the visual appeal of the generated textures. Finally, the results of a user study indicate that our approach generates visually appealing mesh textures that adhere to user-defined guidance and enable users to retain creative control during stylization. Our implementation is available on: https://github.com/AronKovacs/style-brush.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1950, 5415, 1410 ], "articleno": "e70308", "doi": "10.1111/cgf.70308", "issn": "1467-8659", "journal": "Computer Graphics Forum", "pages": "18", "publisher": "WILEY", "research_areas": [], "keywords": [ "3D style transfer", "directional guidance", "mesh texture synthesis", "user guidance" ], "weblinks": [], "files": [], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kovacs-2026-sbg/", "__class": "Publication" }, { "id": "marin-2026-sor", "type_id": "inproceedings", "tu_id": null, "repositum_id": "20.500.12708/227617", "title": "SIGnificant Outlier Removal", "date": "2026-02-10", "abstract": "Point clouds, usually obtained through scanning or various image processing, are commonly affected by noise and outliers. Such artifacts compromise data quality as they significantly distort subsequent processes, such as normal estimation and surface reconstruction. In this work, we introduce a proximity-based outlier removal method for point clouds. We improve on statistical methods based on neighboring graphs by using a parameter-free proximity graph—the spheres-of-influence (SIG), thus requiring fewer parameters compared to classical methods and obtaining better results. Moreover, the simplicity of our method allows it to become an easy replacement for existing statistical methods.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": "booktitle", "repositum_presentation_id": null, "authors": [ 1848, 5593, 948, 193 ], "booktitle": "Computer Vision, Imaging and Computer Graphics Theory and Applications: 19th International Joint Conference, VISIGRAPP 2024, Rome, Italy, February 27–29, 2024, Revised Selected Papers", "date_from": "2024-02-27", "date_to": "2024-02-29", "doi": "10.1007/978-3-032-07623-6_4", "editor": "Bashford-Rogers, Thomas and Meneveaux, Daniel and Ziat, Mounia and Ammi, Mehdi and Jänicke, Stefan and Purchase, Helen and Radeva, Petia and Furnari, Antonino and Bouatouch, Kadi and de Sousa, A. Augusto", "event": "19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2024)", "isbn": "978-3-032-07623-6", "lecturer": [ 1848 ], "location": "Rome", "open_access": "yes", "pages": "14", "pages_from": "67", "pages_to": "80", "publisher": "Springer", "volume": "2548", "research_areas": [], "keywords": [ "Outlier removal", "Point clouds", "Proximity graphs" ], "weblinks": [], "files": [], "projects_workgroups": [ "WorldScale" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/marin-2026-sor/", "__class": "Publication" }, { "id": "erler_philipp-2017-phd", "type_id": "phdthesis", "tu_id": null, "repositum_id": "20.500.12708/228795", "title": "Smart Surface Reconstruction", "date": "2026-02", "abstract": "Point clouds, while easy to acquire, are often noisy, incomplete, and lack connectivity. They cannot represent closed surfaces efficiently, and processing for geometrical applications like 3D printing is difficult. Therefore, we want to convert them to surface representations, most importantly, triangle meshes. This dissertation addresses the challenge of reconstructing accurate and robust 3D objects from imperfect point clouds. Traditional methods struggle with point cloud defects, motivating the exploration of data-driven approaches. However, deep learning on point clouds is difficult due to their unordered and unstructured nature. Further, subsampling is necessary to fit them into the fixed-size input of a neural network, which introduces randomness. In this thesis, we explore solutions for these challenges. We present three main contributions: Points2Surf, which combines local and global priors to generalize surface reconstruction across diverse object classes; PPSurf, which leverages point convolutions and attention to further improve reconstruction quality; and LidarScout, which enables real-time, out-of-core rendering of massive aerial LIDAR scans by focusing on efficient, local heightmap estimation. Our results demonstrate that balancing local detail with global context is key to achieving high-quality, generalizable reconstructions. We show that model design, data augmentation, and efficient representations are crucial for handling noise and missing data. The findings offer practical solutions for reconstructions from single objects to entire landscapes.", "authors_et_al": false, "substitute": null, "main_image": { "description": "Reconstruction, 3D representations", "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1440, "image_height": 501, "name": "erler_philipp-2017-phd-image.png", "type": "image/png", "size": 221151, "path": "Publication:erler_philipp-2017-phd", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/erler_philipp-2017-phd-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/erler_philipp-2017-phd-image:thumb{{size}}.png" }, "sync_repositum_override": "abstract,date,keywords", "repositum_presentation_id": null, "authors": [ 1395 ], "ac_number": "AC17899642", "date_end": "2026-02-11", "date_start": "2017-09", "doi": "10.34726/hss.2026.139540", "duration": "3 years", "open_access": "yes", "pages": "112", "reviewer_1": [ 5558 ], "reviewer_2": [ 1519 ], "rigorosum": "2026-02-11", "supervisor": [ 193 ], "research_areas": [ "Geometry", "Modeling" ], "keywords": [ "Surface Reconstruction", "Deep Learning", "Point Cloud" ], "weblinks": [], "files": [ { "description": "Reconstruction, 3D representations", "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1440, "image_height": 501, "name": "erler_philipp-2017-phd-image.png", "type": "image/png", "size": 221151, "path": "Publication:erler_philipp-2017-phd", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/erler_philipp-2017-phd-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/erler_philipp-2017-phd-image:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "erler_philipp-2017-phd-thesis.pdf", "type": "application/pdf", "size": 5503359, "path": "Publication:erler_philipp-2017-phd", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/erler_philipp-2017-phd-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/erler_philipp-2017-phd-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "ShapeAcquisition", "d4388", "Superhumans" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/erler_philipp-2017-phd/", "__class": "Publication" }, { "id": "chaves-de-plaza-2026-logcc", "type_id": "journalpaper_notalk", "tu_id": null, "repositum_id": "20.500.12708/226667", "title": "LoGCC: Local-to-Global Correlation Clustering for Scalar Field Ensembles", "date": "2026-02", "abstract": "Correlation clustering (CC) offers an effective approach to analyze scalar field ensembles by detecting correlated regions and consistent structures, enabling the extraction of meaningful patterns. However, existing CC methods are computationally expensive, making them impractical for both interactive analysis and large-scale scalar fields. We introduce the Local-to-Global Correlation Clustering (LoGCC) framework, which accelerates pivot-based CC by leveraging the spatial structure of scalar fields and the weak transitivity of correlation. LoGCC operates in two stages: a local step that uses the neighborhood graph of the scalar field's spatial domain to build highly correlated local clusters, and a global step that merges them into global clusters. We implement the LoGCC framework for two well-known pivot-based CC methods, Pivot and CN-Pivot, demonstrating its generality. Our evaluation using synthetic and real-world meteorological and medical image segmentation datasets shows that LoGCC achieves speedups—up to 15 × for Pivot and 200 × for CN-Pivot—and improved scalability to larger scalar fields, while maintaining cluster quality. These contributions broaden the applicability of correlation clustering in large-scale and interactive analysis settings.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5565, 1410, 5566, 5567, 5568, 5569, 5570 ], "doi": "10.1109/TVCG.2025.3630550", "issn": "1941-0506", "journal": "IEEE Transactions on Visualization and Computer Graphics", "number": "2", "pages": "12", "pages_from": "2260", "pages_to": "2271", "publisher": "IEEE COMPUTER SOC", "volume": "32", "research_areas": [], "keywords": [ "Correlation Clustering", "Clustering Algorithms", "Uncertainty Visualization", "Ensemble Visualization", "Scalar Field Ensemble Analysis" ], "weblinks": [], "files": [], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/chaves-de-plaza-2026-logcc/", "__class": "Publication" }, { "id": "kaipel_nikolas-2025-baa", "type_id": "bachelorthesis", "tu_id": null, "repositum_id": null, "title": "Noisy Change Detection", "date": "2026-01-30", "abstract": null, "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image2", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 312, "image_height": 241, "name": "kaipel_nikolas-2025-baa-image2.png", "type": "image/png", "size": 24842, "path": "Publication:kaipel_nikolas-2025-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/kaipel_nikolas-2025-baa-image2.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/kaipel_nikolas-2025-baa-image2:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5444 ], "co_supervisor": [ 948 ], "date_end": "2026-01-30", "date_start": "2025-02-13", "matrikelnr": "12140073", "supervisor": [ 193 ], "research_areas": [ "Geometry" ], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "image2", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 312, "image_height": 241, "name": "kaipel_nikolas-2025-baa-image2.png", "type": "image/png", "size": 24842, "path": "Publication:kaipel_nikolas-2025-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/kaipel_nikolas-2025-baa-image2.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/kaipel_nikolas-2025-baa-image2:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "kaipel_nikolas-2025-baa-thesis.pdf", "type": "application/pdf", "size": 900294, "path": "Publication:kaipel_nikolas-2025-baa", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/kaipel_nikolas-2025-baa-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/kaipel_nikolas-2025-baa-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "WorldScale" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/kaipel_nikolas-2025-baa/", "__class": "Publication" }, { "id": "fitz-2026-isc", "type_id": "masterthesis", "tu_id": null, "repositum_id": "20.500.12708/229084", "title": "Interactive Sampling for Class Discovery in Unstructured Data", "date": "2026", "abstract": "Analyzing unstructured data such as images presents a major challenge for exploratory data analysis due to their high dimensionality. The data must first be transformed into embeddings, which results in lower dimensionality where the data are more closely grouped. Sampling is essential to make these datasets more understandable for humans through visualization. This work aims to explore how interactive systems can provide representative and interpretable samples quickly, even from large and unbalanced image datasets. Standard methods like random sampling can reach their limits and often fail to capture rare classes, leading to biases in interpretation. Within a standardized interaction protocol, various data-driven strategies (e.g., farthest sampling and Dα sampling) and model-aware strategies (e.g., min-margin and disagreement) are compared with random sampling. The goal is to investigate which strategies offer the best balance between fast class discovery, high model accuracy, and low latency within a defined interaction budget. The results show that data-driven methods are strong in the early stages of the iterative process, as they explore the data space and lead to faster discovery of new classes. In contrast, model-aware methods offer advantages in later stages, as they refine the decision boundaries and efficiently increase accuracy as labeled data become available. The superiority of targeted sampling over random sampling is particularly evident with unbalanced datasets. Furthermore, the work shows that GPU acceleration reduces latency in the iterative cycle, thus maintaining the critical threshold of less than one second per selection step, enabling smooth interactions.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": "projects", "repositum_presentation_id": null, "authors": [ 5603 ], "ac_number": "AC17909432", "co_supervisor": [ 5604 ], "date_end": "2026-06", "doi": "10.34726/hss.2026.136745", "open_access": "yes", "pages": "106", "supervisor": [ 1110 ], "research_areas": [ "InfoVis" ], "keywords": [ "Sampling", "Human-AI Collaboration", "Visual Analysis", "Unstructured Data" ], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "fitz-2026-isc-thesis.pdf", "type": "application/pdf", "size": 2616425, "path": "Publication:fitz-2026-isc", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/fitz-2026-isc/fitz-2026-isc-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/fitz-2026-isc/fitz-2026-isc-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "d9282" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/fitz-2026-isc/", "__class": "Publication" }, { "id": "peterka-2026-ips", "type_id": "masterthesis", "tu_id": null, "repositum_id": "20.500.12708/228067", "title": "Informed Patch Sampling for 3D Medical Image Reconstruction", "date": "2026", "abstract": "Efficient analysis and processing of 3D volumes are crucial in clinical practice. A common task in 3D medical image processing is object segmentation, where objects of interest are delineated. However, segmenting large volumetric scans requires substantial memory and computational power, making end-to-end segmentation both memory- and computationally intensive. A potential solution to reduce these costs is to select only a subset of the input, segment this subset, and estimate the values of the remaining regions by reconstructing them from the segmented subset. Our hypothesis is that the choice of subset influences reconstruction performance, with some regions of the input volume being more informative for reconstruction than others. To test this hypothesis, we propose a neural network capable of identifying subsets that contribute most to accurate reconstruction. To simplify the process and focus on the core task, we assume that binary segmentations of the objects of interest are provided and select subsets directly from them, reconstructing the original binary segmentations afterwards. We build our neural network upon an existing point cloud-based network that learns to select representative points, and integrate it into a novel end-to-end pipeline for reconstructing full volumes from limited input data. We modify the original point cloud–based loss function to operate on voxel grid data and introduce conversion and extraction mechanisms that enable transitions between voxel grid and point cloud representations. Our proposed pipeline first converts the input voxel grid into a point cloud representation to enable efficient geometric processing. A neural network architecture then processes the point cloud and predicts a set of candidate centers for volumetric patches. These predicted centers are subsequently used to extract the output patch set, which is then fed to the downstream reconstruction network. We evaluate our pipeline on two datasets of medical shape segmentations with varying geometrical complexity. Our experiments show that the proposed learned sampler identifies informative regions, which support reconstruction performance, especially for complex shapes and limited spatial context. We further evaluate the effect of reconstruction network quality across different input configurations, varying patch size and number of patches, and show that our approach is effective when reconstruction accuracy is poor or when the input shape has complex geometry. Finally, we analyze the computations and memory demands of the proposed pipeline, showing that the additional overhead remains under 1 GB of memory and 0.5 s of extra computation, making the method suitable for deployment in resource-limited environments.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1948 ], "ac_number": "AC17859583", "doi": "10.34726/hss.2026.128140", "open_access": "yes", "pages": "122", "supervisor": [ 1410 ], "research_areas": [], "keywords": [ "Medical Image Analysis", "Segmentation", "Data Sampling", "3D Data Processing", "Deep Learning", "Image Reconstruction" ], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "peterka-2026-ips-thesis.pdf", "type": "application/pdf", "size": 5443632, "path": "Publication:peterka-2026-ips", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/peterka-2026-ips/peterka-2026-ips-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/peterka-2026-ips/peterka-2026-ips-thesis:thumb{{size}}.png" } ], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/peterka-2026-ips/", "__class": "Publication" }, { "id": "Kovacs_PhD", "type_id": "phdthesis", "tu_id": null, "repositum_id": "20.500.12708/224033", "title": "3D Style Transfer: Lifting 2D Methods to 3D and Enabling Interactive Guidance", "date": "2026", "abstract": "3D style transfer refers to altering the visual appearance of 3D objects and scenes to match a given (artistic) style, usually provided as an image. 3D style transfer presents significant potential in streamlining the creation of 3D assets such as game environment props, VFX elements, or largescale virtual scenes. However, it faces challenges such as ensuring multi-view consistency, respecting computational and memory constraints, and enabling artist control. In this dissertation, we propose three methods that aim at stylizing 3D assets while addressing these challenges. We focus on optimization-based methods due to the higher quality of results compared to single-pass methods. 0ur contributions advance the state-of-the-art by introducing: (i) novel surface-aware CNN operators for direct mesh texturing, (ii) the first Gaussian Splatting (GS) method capable of transferring both high-frequency details and large scale patterns, and (iii) an interactive method that allows directional and region-based control over the stylization process. Each of these methods outperforms existing baselines in visual fidelity and robustness. Across three complementary projects, we explore different facets of 3D style transfer. In the first project, we propose a method that creates textures directly on the surface of a mesh. By replacing the standard 2D convolution and pooling layers in a pre-trained 2D CNN with surface-based operations, we achieve seamless, multi-view-consistent texture synthesis without relying on proxy 2D images. In the second project, we transfer both high-frequency and large-scale patterns using GS, while addressing representation-specific artifacts such as oversized or elongated Gaussians. Furthermore, we design a style loss capable of transferring style patterns at multiple scales, resulting in visually appealing stylized scenes that preserve both intricate details and large-scale motifs. In the third project, we propose an interactive method that allows users to guide stylization by drawing lines to control pattern direction, and painting regions on both the 3D surface and style image to specify where and how specific style patterns should be applied. Through our extensive qualitative and quantitative evaluations, we show that our methods surpass state-of-the-art techniques. We also demonstrate their robustness across diverse 3D objects, scenes, and styles, highlighting the flexibility of the presented methods. Future work may explore extensions such as geometry modification for style-driven shape changes, more efficient !arge-scale pattern synthesis, temporal coherence in dynamic or video-based scenes, and refined interactive controls informed by direct artist feedback to better integrate creative intent into the stylization pipeline.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": "title,abstract,date,keywords,type_id", "repositum_presentation_id": null, "authors": [ 1950 ], "ac_number": "AC17745734", "co_supervisor": [ 5572 ], "date_end": "2024", "date_start": "2021", "doi": "10.34726/hss.2026.137815", "open_access": "yes", "pages": "104", "supervisor": [ 1410 ], "research_areas": [ "MedVis" ], "keywords": [ "Style transfer", "Texture synthesis", "Neural Networks", "Neural rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "Kovacs_PhD-thesis.pdf", "type": "application/pdf", "size": 4807053, "path": "Publication:Kovacs_PhD", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/Kovacs_PhD/Kovacs_PhD-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/Kovacs_PhD/Kovacs_PhD-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "vis" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/Kovacs_PhD/", "__class": "Publication" }, { "id": "siemers-2026-ibl", "type_id": "masterthesis", "tu_id": null, "repositum_id": "20.500.12708/227823", "title": "Image Based Level-of-Detail Construction for Novel View Synthesis", "date": "2026", "abstract": "This thesis presents a coarse-to-fine optimisation method for 3D Gaussian Splatting(3DGS) that constructs a Level of Detail (LoD) hierarchy during optimisation, which can be rendered selectively. By gradually adjusting the resolution, the method reduces computational effort, speeds up optimisation and generates a LoD hierarchy in the process.Based on the sampling rate, defined as the ratio of the resolution at which the model was optimised to that at which it is viewed, a selective rendering method is presented. Selective rendering reduces the number of primitives processed and mitigates aliasing errors, at the cost of increased memory usage on the Graphics Processing Unit (GPU) due to multiple independent LoD levels. The method is evaluated using 3DGS and Elliptical Weighted Average (EWA)-filtering as a basis for comparison on common 360◦ and aerialimage datasets, with a focus on low-resolution renderings and distant viewpoints.The results show that the method speeds up optimisation and reduces the number of processed primitives. Particularly for distant or low-resolution views, images are generated more quickly, and aliasing errors are reduced. At full resolution, the visual quality remains approximately the same as the baseline. Although the method requires additional GPU memory during rendering, it offers a practical approach to faster optimisation of more compact models that are rendered with reduced aliasing.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5595 ], "ac_number": "AC17849014", "co_supervisor": [ 1848 ], "doi": "10.34726/hss.2026.135800", "open_access": "yes", "pages": "76", "supervisor": [ 1720 ], "research_areas": [], "keywords": [ "Novel View Synthesis", "Level-of-Detail", "Anti-Aliasing", "Gaussian Splatting", "Rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "siemers-2026-ibl-thesis.pdf", "type": "application/pdf", "size": 2839187, "path": "Publication:siemers-2026-ibl", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/siemers-2026-ibl/siemers-2026-ibl-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/siemers-2026-ibl/siemers-2026-ibl-thesis:thumb{{size}}.png" } ], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/siemers-2026-ibl/", "__class": "Publication" }, { "id": "stadter-2026-vas", "type_id": "masterthesis", "tu_id": null, "repositum_id": "20.500.12708/228859", "title": "Visual Analytics Support for Chemotherapy Treatment Response Prediction in Breast Cancer Patients", "date": "2026", "abstract": "Predicting treatment response in breast cancer patients undergoing neoadjuvant chemotherapy remains challenging, due to the substantial variation in how tumors respond to treatment. This thesis investigates whether mathematical tumor growth modeling, specifically the Simeoni model, can enhance a typical radiomics-based treatment response classification analysis. We analyzed Diffusion Weighted Imaging (DWI) data from 162 patients in the ACRIN6698 trial across four imaging timepoints during their treatment, extracted 428 radiomic features and 15 Simeoni-derived mechanistic features, and trained 116 Random Forest model configurations across different feature sets and timepoint combinations using Leave-One-Out Cross-Validation for five-class treatment response classification. An interactive visual analytics dashboard was finally developed for the systematic exploration of the experimental space. The best model achieved 90.1% accuracy using radiomics-only features from all four imaging timepoints. Combined models with Simeoni features consistently underperformed, with accuracy reductions ranging from 2.4% to 6.2%. Multi-timepoint imaging was the strongest predictor of accuracy, increasing performance from 71.6% with baseline data to 90.1% with all timepoints. Statistical analysis confirmed that Simeoni features are redundant with multi-timepoint radiomic features rather than being complementary. For clinical application, radiomics-only models are recommended for treatment response classification. The Simeoni model provides biological insight into tumor dynamics but does not enhance classification performance.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5601 ], "ac_number": "AC17900963", "doi": "10.34726/hss.2026.117601", "open_access": "yes", "pages": "196", "supervisor": [ 1410 ], "research_areas": [], "keywords": [ "Brustkrebs", "Neoadjuvante Chemotherapie", "Vorhersage des Therapieansprechens", "Radiomics", "Diffusion Weighted Imaging", "Tumorwachstumsmodellierung", "Simeoni-Modell", "Maschinelles Lernen", "Visual Analytics", "Feature-Redundanz" ], "weblinks": [], "files": [ { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "name": "stadter-2026-vas-thesis.pdf", "type": "application/pdf", "size": 4122106, "path": "Publication:stadter-2026-vas", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/stadter-2026-vas/stadter-2026-vas-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/stadter-2026-vas/stadter-2026-vas-thesis:thumb{{size}}.png" } ], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/stadter-2026-vas/", "__class": "Publication" }, { "id": "stoiber-2026-v2e", "type_id": "proceedings", "tu_id": null, "repositum_id": "20.500.12708/229114", "title": "Visgames 2026: EuroVis Workshop on Visualization Play, Games, and Activities", "date": "2026", "abstract": "We are happy to announce that the second Workshop on Visualization, Play, Games, and Activities: Vis-Games will take place as part of the EuroVis Conference on June 8, 2026, in Nottingham, UK.\nVisGames explores how visualization games and playful activities can be used beyond education as tools for communication, co-creation, and collaborative problem-solving. With this workshop, we aim to high-light innovative approaches that foster idea generation, support decision-making, engage stakeholders, and evaluate visualization design through interactive and game-based methods.", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": "authors", "repositum_presentation_id": null, "authors": [ 5489, 5417, 1861, 5606, 1410, 1464, 5607, 5608, 5609 ], "doi": "10.2312/visgames.20262000", "editor": "Stoiber, Christina and Filipov, Velitchko and Amabili, Lorenzo and Keck, Mandy and Raidou, Renata Georgia and Wu, Hsiang-Yun and Boucher, Magdalena and Kriglstein, Simone and De-Jesus-Oliveira, Victor-Adriel", "publisher": "The Eurographics Association", "research_areas": [], "keywords": [ "Visualization", "Games", "Activities", "Co-Design", "Co-Creation" ], "weblinks": [], "files": [], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/stoiber-2026-v2e/", "__class": "Publication" }, { "id": "grammatikaki-2026-treeon", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/228171", "title": "TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps", "date": "2026", "abstract": "We present TreeON, a novel neural-based framework for reconstructing detailed 3D tree point clouds from sparse top-down geodata, using only a single orthophoto and its corresponding Digital Surface Model (DSM). Our method introduces a new training supervision strategy that combines both geometric supervision and a differentiable shadow and silhouette loss to learn point cloud representations of trees without requiring species labels, procedural rules, detailed terrestrial reconstruction data, or ground laser scan data. To address the lack of ground truth data, we generate a synthetic dataset of point clouds from procedurally modeled trees and train our network on it. Quantitative and qualitative experiments demonstrate better reconstruction quality and coverage compared to existing methods, as well as strong generalization to real-world data, leading to visually appealing and structurally plausible tree point cloud representations that can be integrated into interactive digital 3D maps. The codebase, synthetic dataset, and pretrained model are publicly available at https://angelikigram.github.io/treeON/.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1698, "image_height": 496, "name": "grammatikaki-2026-treeon-teaser.png", "type": "image/png", "size": 1175153, "path": "Publication:grammatikaki-2026-treeon", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/grammatikaki-2026-treeon-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/grammatikaki-2026-treeon-teaser:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1937, 1653, 5415, 5462, 1110 ], "articleno": "e70366", "doi": "10.1111/cgf.70366", "issn": "1467-8659", "journal": "Computer Graphics Forum", "open_access": "yes", "pages": "14", "publisher": "WILEY", "research_areas": [], "keywords": [ "Computing methodologies", "Point-based models", "Reconstruction", "Neural Networks" ], "weblinks": [ { "href": "https://angelikigram.github.io/treeON/", "caption": null, "description": null, "main_file": 0 } ], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "grammatikaki-2026-treeon-paper.pdf", "type": "application/pdf", "size": 70465234, "path": "Publication:grammatikaki-2026-treeon", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/grammatikaki-2026-treeon-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/grammatikaki-2026-treeon-paper:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1698, "image_height": 496, "name": "grammatikaki-2026-treeon-teaser.png", "type": "image/png", "size": 1175153, "path": "Publication:grammatikaki-2026-treeon", "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/grammatikaki-2026-treeon-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/grammatikaki-2026-treeon-teaser:thumb{{size}}.png" } ], "projects_workgroups": [ "d10164", "d9275" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/", "__class": "Publication" } ]