[ { "id": "erler-2025-lidarscout", "type_id": "inproceedings", "tu_id": null, "repositum_id": "20.500.12708/216864", "title": "LidarScout: Direct Out-of-Core Rendering of Massive Point Clouds", "date": "2025-06", "abstract": "Large-scale terrain scans are the basis for many important tasks, such as topographic mapping, forestry, agriculture, and infrastructure planning. The resulting point cloud data sets are so massive in size that even basic tasks like viewing take hours to days of pre-processing in order to create level-of-detail structures that allow inspecting the data set in their entirety in real time. In this paper, we propose a method that is capable of instantly visualizing massive country-sized scans with hundreds of billions of points. Upon opening the data set, we first load a sparse subsample of points and initialize an overview of the entire point cloud, immediately followed by a surface reconstruction process to generate higher-quality, hole-free heightmaps. As users start navigating towards a region of interest, we continue to prioritize the heightmap construction process to the user's viewpoint. Once a user zooms in closely, we load the full-resolution point cloud data for that region and update the corresponding height map textures with the full-resolution data. As users navigate elsewhere, full-resolution point data that is no longer needed is unloaded, but the updated heightmap textures are retained as a form of medium level of detail. Overall, our method constitutes a form of direct out-of-core rendering for massive point cloud data sets (terabytes, compressed) that requires no preprocessing and no additional disk space. Source code, executable, pre-trained model, and dataset are available at: https://github.com/cg-tuwien/lidarscout", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 2456, "image_height": 1411, "name": "erler-2025-lidarscout-teaser.jpg", "type": "image/jpeg", "size": 421958, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-teaser.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-teaser:thumb{{size}}.png" }, "sync_repositum_override": "date,projects,articleno", "repositum_presentation_id": null, "authors": [ 1395, 1857, 193, 1116 ], "articleno": "10.2312/hpg.20251170", "booktitle": "High-Performance Graphics 2025 - Symposium Papers", "date_from": "2025-06-23", "date_to": "2025-06-25", "doi": "10.2312/hpg.20251170", "event": "High-Performance Graphics 2025", "isbn": "978-3-03868-291-2", "lecturer": [ 1395 ], "location": "Koppenhagen", "pages": "11", "publisher": "the Eurographics Association", "research_areas": [ "Geometry", "Modeling" ], "keywords": [ "Point-based models", "Mesh models", "Neural networks", "Reconstruction", "Aerial LIDAR" ], "weblinks": [ { "href": "https://github.com/cg-tuwien/lidarscout", "caption": "Repository of Viewer Source", "description": null, "main_file": 1 }, { "href": "https://github.com/cg-tuwien/lidarscout_training", "caption": "Repository of Training Source", "description": null, "main_file": 1 }, { "href": "https://www.youtube.com/watch?v=q7Ap-FHZufY&list=PLD5wBo3-8n8LVGp6BDOFuPgGANdoYg_uk&index=8", "caption": "Presentation from HPG 2025", "description": null, "main_file": 1 }, { "href": "https://doi.org/10.48436/443tr-j4096", "caption": "TUW Research Data Repository", "description": "Datasets, models, more results", "main_file": 0 } ], "files": [ { "description": "Datasets for training and testing, containing chunk points and GT patches", "filetitle": "Datasets", "main_file": false, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-Datasets.zip", "type": "application/x-zip-compressed", "size": 3201189460, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Datasets.zip", "thumb_image_sizes": [] }, { "description": "Models with checkpoints, training logs, hyperparameters and TorchScript", "filetitle": "Models", "main_file": false, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-Models.zip", "type": "application/x-zip-compressed", "size": 185148024, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Models.zip", "thumb_image_sizes": [] }, { "description": null, "filetitle": "Paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-Paper.pdf", "type": "application/pdf", "size": 41113068, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Paper:thumb{{size}}.png" }, { "description": "Results CNN Allstar (more training data, best results)", "filetitle": "Results_best", "main_file": false, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-Results_best.zip", "type": "application/x-zip-compressed", "size": 2019427310, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Results_best.zip", "thumb_image_sizes": [] }, { "description": "Results CNN (main method)", "filetitle": "Results_main", "main_file": false, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-Results_main.zip", "type": "application/x-zip-compressed", "size": 1781055950, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Results_main.zip", "thumb_image_sizes": [] }, { "description": null, "filetitle": "teaser_large", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 2480, "image_height": 965, "name": "erler-2025-lidarscout-teaser_large.jpg", "type": "image/jpeg", "size": 403739, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-teaser_large.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-teaser_large:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 2456, "image_height": 1411, "name": "erler-2025-lidarscout-teaser.jpg", "type": "image/jpeg", "size": 421958, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-teaser.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-teaser:thumb{{size}}.png" }, { "description": "A screen capture of the viewer", "filetitle": "video", "main_file": true, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-video.mp4", "type": "video/mp4", "size": 122979998, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-video.mp4", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-video:thumb{{size}}.png", "video_mp4": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-video:video.mp4" }, { "description": "LidarScout Executable for Windows", "filetitle": "Viewer", "main_file": true, "use_in_gallery": false, "access": "public", "name": "erler-2025-lidarscout-Viewer.zip", "type": "application/x-zip-compressed", "size": 2360647751, "path": "Publication:erler-2025-lidarscout", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/erler-2025-lidarscout-Viewer.zip", "thumb_image_sizes": [] } ], "projects_workgroups": [ "d9275", "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2025/erler-2025-lidarscout/", "__class": "Publication" }, { "id": "schuetz-2025-splatshop", "type_id": "journalpaper_notalk", "tu_id": null, "repositum_id": "20.500.12708/216694", "title": "Splatshop: Efficiently Editing Large Gaussian Splat Models", "date": "2025-06", "abstract": "We present Splatshop, a highly optimized toolbox for interactive editing (selection, deletion, painting, transformation, . . . ) of 3D Gaussian Splatting models. Utilizing a comprehensive collection of heuristic approaches, we carefully balance between exact and fast rendering to enable precise editing without sacrificing real-time performance. Our experiments confirm that Splatshop achieves these goals for scenes with up to 100 million primitives. We also show how our proposed pipeline can be extended for use with head-mounted displays. As such, Splatshop is the first VR-capable editor for large-scale 3D Gaussian Splatting models and a step towards a ''Photoshop for Gaussian Splatting.''", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "cover", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1276, "image_height": 691, "name": "schuetz-2025-splatshop-cover.jpg", "type": "image/jpeg", "size": 327472, "path": "Publication:schuetz-2025-splatshop", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/schuetz-2025-splatshop/schuetz-2025-splatshop-cover.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/schuetz-2025-splatshop/schuetz-2025-splatshop-cover:thumb{{size}}.png" }, "sync_repositum_override": "date,projects,articleno", "repositum_presentation_id": null, "authors": [ 1116, 5492, 5493, 823, 842, 193 ], "articleno": "8", "doi": "10.1111/cgf.70214", "issn": "1467-8659", "journal": "Computer Graphics Forum", "note": "https://github.com/m-schuetz/Splatshop", "number": "8", "open_access": "yes", "pages": "12", "publisher": "WILEY", "volume": "44", "research_areas": [ "Rendering" ], "keywords": [ "gaussian splats", "point clouds", "real-time rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "cover", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1276, "image_height": 691, "name": "schuetz-2025-splatshop-cover.jpg", "type": "image/jpeg", "size": 327472, "path": "Publication:schuetz-2025-splatshop", "url": "https://www.cg.tuwien.ac.at/research/publications/2025/schuetz-2025-splatshop/schuetz-2025-splatshop-cover.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2025/schuetz-2025-splatshop/schuetz-2025-splatshop-cover:thumb{{size}}.png" } ], "projects_workgroups": [ "d9275", "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2025/schuetz-2025-splatshop/", "__class": "Publication" }, { "id": "goel-2024-rdr", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/204000", "title": "Real-Time Decompression and Rasterization of Massive Point Clouds", "date": "2024-08-09", "abstract": "Large-scale capturing of real-world scenes as 3D point clouds (e.g., using LIDAR scanning) generates billions of points that are challenging to visualize. High storage requirements prevent the quick and easy inspection of captured datasets on user-grade hardware. The fastest real-time rendering methods are limited by the available GPU memory and render only around 1 billion points interactively. We show that we can achieve state-of-the-art in both while simultaneously supporting datasets that surpass the capabilities of other methods. We present an on-the-fly point cloud decompression scheme that tightly integrates with software rasterization to reduce on-chip memory requirements by more than 4×. Our method compresses geometry losslessly and provides high visual quality at real-time framerates. We use a GPU-friendly, clipped Huffman encoding for compression. Point clouds are divided into equal-sized batches, which are Huffman-encoded independently. Batches are further subdivided to form easy-to-consume streams of data for massively parallel execution. The compressed point clouds are stored in an access-aware manner to achieve coherent GPU memory access and a high L1 cache hit rate at render time. Our approach can decompress and rasterize up to 120 million Huffman-encoded points per millisecond on-the-fly. We evaluate the quality and performance of our approach on various large datasets against the fastest competing methods. Our approach renders massive 3D point clouds at competitive frame rates and visual quality while consuming significantly less memory, thus unlocking unprecedented performance for the visualization of challenging datasets on commodity GPUs.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "cover", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1695, "image_height": 961, "name": "goel-2024-rdr-cover.jpg", "type": "image/jpeg", "size": 276042, "path": "Publication:goel-2024-rdr", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/goel-2024-rdr/goel-2024-rdr-cover.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/goel-2024-rdr/goel-2024-rdr-cover:thumb{{size}}.png" }, "sync_repositum_override": "projects,date_from,date_to,event,lecturer,location", "repositum_presentation_id": null, "authors": [ 5402, 1116, 5403, 1650 ], "articleno": "48", "date_from": "2024-06-26", "date_to": "2024-06-28", "doi": "10.1145/3675373", "event": "High Performance Graphics", "issn": "2577-6193", "journal": "Proceedings of the ACM on Computer Graphics and Interactive Techniques", "lecturer": [ 1116 ], "location": "Denver, USA", "number": "3", "pages": "15", "pages_from": "1", "pages_to": "15", "publisher": "Association for Computing Machinery (ACM)", "volume": "7", "research_areas": [ "Rendering" ], "keywords": [ "compression", "point cloud", "rasterization", "real-time rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "cover", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1695, "image_height": 961, "name": "goel-2024-rdr-cover.jpg", "type": "image/jpeg", "size": 276042, "path": "Publication:goel-2024-rdr", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/goel-2024-rdr/goel-2024-rdr-cover.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/goel-2024-rdr/goel-2024-rdr-cover:thumb{{size}}.png" } ], "projects_workgroups": [ "rend", "d9275" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2024/goel-2024-rdr/", "__class": "Publication" }, { "id": "SCHUETZ-2024-SIMLOD", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/208716", "title": "SimLOD: Simultaneous LOD Generation and Rendering for Point Clouds", "date": "2024-05-13", "abstract": "LOD construction is typically implemented as a preprocessing step that requires users to wait before they are able to view the results in real time. We propose an incremental LOD generation approach for point clouds that allows us to simultaneously load points from disk, update an octree-based level-of-detail representation, and render the intermediate results in real time while additional points are still being loaded from disk. LOD construction and rendering are both implemented in CUDA and share the GPU’s processing power, but each incremental update is lightweight enough to leave enough time to maintain real-time frame rates. Our approach is able to stream points from an SSD and update the octree on the GPU at rates of up to 580 million points per second (~9.3GB/s) on an RTX 4090 and a PCIe 5.0 SSD. Depending on the data set, our approach spends an average of about 1 to 2 ms to incrementally insert 1 million points into the octree, allowing us to insert several million points per frame into the LOD structure and render the intermediate results within the same frame.", "authors_et_al": false, "substitute": null, "main_image": { "description": "Rendered Point Cloud to the left and points/voxels colored by the containing octree node to the right.", "filetitle": "SimLOD", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1911, "image_height": 1072, "name": "SCHUETZ-2024-SIMLOD-SimLOD.jpg", "type": "image/jpeg", "size": 323598, "path": "Publication:SCHUETZ-2024-SIMLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/SCHUETZ-2024-SIMLOD-SimLOD.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/SCHUETZ-2024-SIMLOD-SimLOD:thumb{{size}}.png" }, "sync_repositum_override": "event", "repositum_presentation_id": null, "authors": [ 1116, 1857, 193 ], "articleno": "17", "date_from": "2023-05", "date_to": "2023-05", "doi": "10.1145/3651287", "event": "ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games 2024", "issn": "2577-6193", "journal": "Proceedings of the ACM on Computer Graphics and Interactive Techniques", "lecturer": [ 1116 ], "note": "Source Code: https://github.com/m-schuetz/SimLOD", "number": "1", "open_access": "yes", "pages": "20", "publisher": "Association for Computing Machinery (ACM)", "volume": "7", "research_areas": [ "Rendering" ], "keywords": [ "LOD", "real-time rendering", "Point Cloud Rendering", "rasterization", "Octree" ], "weblinks": [], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2024-SIMLOD-paper.pdf", "type": "application/pdf", "size": 5928589, "path": "Publication:SCHUETZ-2024-SIMLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/SCHUETZ-2024-SIMLOD-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/SCHUETZ-2024-SIMLOD-paper:thumb{{size}}.png" }, { "description": "Rendered Point Cloud to the left and points/voxels colored by the containing octree node to the right.", "filetitle": "SimLOD", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1911, "image_height": 1072, "name": "SCHUETZ-2024-SIMLOD-SimLOD.jpg", "type": "image/jpeg", "size": 323598, "path": "Publication:SCHUETZ-2024-SIMLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/SCHUETZ-2024-SIMLOD-SimLOD.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/SCHUETZ-2024-SIMLOD-SimLOD:thumb{{size}}.png" } ], "projects_workgroups": [ "d9275", "d4386" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2024/SCHUETZ-2024-SIMLOD/", "__class": "Publication" }, { "id": "unterguggenberger-2024-fropo", "type_id": "inproceedings", "tu_id": null, "repositum_id": "20.500.12708/199275", "title": "Fast Rendering of Parametric Objects on Modern GPUs", "date": "2024-05", "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, 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. This has given rise to several specialized solutions, each targeting interactive rendering of a constrained set of parametric functions. In this paper, we propose a general method for efficient rendering of parametrically defined 3D objects. Our solution is carefully designed around modern hardware architecture. 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 level-of-detail (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 softare 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, while showing its flexibility on a range of other demanding shapes.", "authors_et_al": false, "substitute": null, "main_image": { "description": "Teaser image, different parametric objects", "filetitle": "image", "main_file": true, "use_in_gallery": true, "access": "public", "image_width": 1440, "image_height": 1364, "name": "unterguggenberger-2024-fropo-image.png", "type": "image/png", "size": 2235242, "path": "Publication:unterguggenberger-2024-fropo", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/unterguggenberger-2024-fropo-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/unterguggenberger-2024-fropo-image:thumb{{size}}.png" }, "sync_repositum_override": "date,projects", "repositum_presentation_id": null, "authors": [ 848, 1525, 193, 1650, 1116 ], "booktitle": "EGPGV24: Eurographics Symposium on Parallel Graphics and Visualization", "date_from": "2024-05-27", "date_to": "2024-05-27", "doi": "10.2312/pgv.20241129", "event": "Eurographics Symposium on Parallel Graphics and Visualization (2024)", "isbn": "978-3-03868-243-1", "lecturer": [ 848 ], "location": "Odense", "open_access": "yes", "pages": "12", "publisher": "The Eurographics Association", "research_areas": [ "Rendering" ], "keywords": [ "Tessellation Shaders", "Point-Based Rendering", "Parametric Objects", "Fast Rendering", "Modern GPUs" ], "weblinks": [ { "href": "https://github.com/cg-tuwien/FastRenderingOfParametricObjects", "caption": "FastRenderingOfParametricObjects", "description": "Source Code on GitHub", "main_file": 0 } ], "files": [ { "description": "Teaser image, different parametric objects", "filetitle": "image", "main_file": true, "use_in_gallery": true, "access": "public", "image_width": 1440, "image_height": 1364, "name": "unterguggenberger-2024-fropo-image.png", "type": "image/png", "size": 2235242, "path": "Publication:unterguggenberger-2024-fropo", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/unterguggenberger-2024-fropo-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/unterguggenberger-2024-fropo-image:thumb{{size}}.png" }, { "description": "Published Paper", "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "unterguggenberger-2024-fropo-paper.pdf", "type": "application/pdf", "size": 17591180, "path": "Publication:unterguggenberger-2024-fropo", "url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/unterguggenberger-2024-fropo-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/unterguggenberger-2024-fropo-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d9275", "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2024/unterguggenberger-2024-fropo/", "__class": "Publication" }, { "id": "SCHUETZ-2023-LOD", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/191989", "title": "GPU‐Accelerated LOD Generation for Point Clouds", "date": "2023-06", "abstract": "About:\nWe introduce a GPU-accelerated LOD construction process that creates a hybrid voxel-point-based variation of the widely used layered point cloud (LPC) structure for LOD rendering and streaming. The massive performance improvements provided by the GPU allow us to improve the quality of lower LODs via color filtering while still increasing construction speed compared to the non-filtered, CPU-based state of the art.\n\n\nBackground: \nLOD structures are required to render hundreds of millions to trillions of points, but constructing them takes time.\n\n\nResults: \nLOD structures suitable for rendering and streaming are constructed at rates of about 1 billion points per second (with color filtering) to 4 billion points per second (sample-picking/random sampling, state of the art) on an RTX 3090 -- an improvement of a factor of 80 to 400 times over the CPU-based state of the art (12 million points per second). Due to being in-core, model sizes are limited to about 500 million points per 24GB memory.\n\n\nDiscussion: \nOur method currently focuses on maximizing in-core construction speed on the GPU. Issues such as out-of-core construction of arbitrarily large data sets are not addressed, but we expect it to be suitable as a component of bottom-up out-of-core LOD construction schemes.", "authors_et_al": false, "substitute": null, "main_image": { "description": "Teaser Figure. ", "filetitle": "CudaLOD", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1442, "image_height": 884, "name": "SCHUETZ-2023-LOD-CudaLOD.jpg", "type": "image/jpeg", "size": 226119, "path": "Publication:SCHUETZ-2023-LOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/SCHUETZ-2023-LOD-CudaLOD.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/SCHUETZ-2023-LOD-CudaLOD:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 1650, 1802, 193 ], "articleno": "e14877", "date_from": "2023", "date_to": "2023", "doi": "10.1111/cgf.14877", "event": "High Performance Graphics", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1116 ], "location": "Delft", "number": "8", "open_access": "yes", "pages": "12", "pages_from": "1", "pages_to": "12", "publisher": "WILEY", "volume": "42", "research_areas": [ "Rendering" ], "keywords": [ "point cloud rendering", "level of detail", "LOD" ], "weblinks": [ { "href": "https://github.com/m-schuetz/CudaLOD", "caption": "Source Code", "description": null, "main_file": 0 } ], "files": [ { "description": "Teaser Figure. ", "filetitle": "CudaLOD", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1442, "image_height": 884, "name": "SCHUETZ-2023-LOD-CudaLOD.jpg", "type": "image/jpeg", "size": 226119, "path": "Publication:SCHUETZ-2023-LOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/SCHUETZ-2023-LOD-CudaLOD.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/SCHUETZ-2023-LOD-CudaLOD:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": false, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2023-LOD-paper.pdf", "type": "application/pdf", "size": 12634836, "path": "Publication:SCHUETZ-2023-LOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/SCHUETZ-2023-LOD-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/SCHUETZ-2023-LOD-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "d4386" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2023/SCHUETZ-2023-LOD/", "__class": "Publication" }, { "id": "SCHUETZ-2022-PCC", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/193255", "title": "Software Rasterization of 2 Billion Points in Real Time", "date": "2022-07", "abstract": "We propose a software rasterization pipeline for point clouds that is capable of brute-force rendering up to two billion points in real time (60fps). Improvements over the state of the art are achieved by batching points in a way that a number of batch-level optimizations can be computed before rasterizing the points within the same rendering pass. These optimizations include frustum culling, level-of-detail rendering, and choosing the appropriate coordinate precision for a given batch of points directly within a compute workgroup. Adaptive coordinate precision, in conjunction with visibility buffers, reduces the number of loaded bytes for the majority of points down to 4, thus making our approach several times faster than the bandwidth-limited state of the art. Furthermore, support for LOD rendering makes our software-rasterization approach suitable for rendering arbitrarily large point clouds, and to meet the increased performance demands of virtual reality rendering. ", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 516, "image_height": 368, "name": "SCHUETZ-2022-PCC-teaser.png", "type": "image/png", "size": 291356, "path": "Publication:SCHUETZ-2022-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/SCHUETZ-2022-PCC-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/SCHUETZ-2022-PCC-teaser:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 1650, 193 ], "cfp": { "name": "cfp.pdf", "type": "application/pdf", "error": "0", "size": "1439654", "orig_name": "cfp.pdf", "ext": "pdf" }, "date_from": "2022-07-11", "date_to": "2022-07-14", "doi": "10.1145/3543863", "event": "High Performance Graphics 2022", "issn": "2577-6193", "journal": "Proceedings of the ACM on Computer Graphics and Interactive Techniques", "lecturer": [ 1116 ], "location": "Vancouver", "number": "3", "open_access": "yes", "pages": "17", "pages_from": "1", "pages_to": "17", "publisher": "Association for Computing Machinery (ACM)", "volume": "5", "research_areas": [ "Geometry", "Rendering" ], "keywords": [ "point-based rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2022-PCC-paper.pdf", "type": "application/pdf", "size": 7306416, "path": "Publication:SCHUETZ-2022-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/SCHUETZ-2022-PCC-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/SCHUETZ-2022-PCC-paper:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 516, "image_height": 368, "name": "SCHUETZ-2022-PCC-teaser.png", "type": "image/png", "size": 291356, "path": "Publication:SCHUETZ-2022-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/SCHUETZ-2022-PCC-teaser.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/SCHUETZ-2022-PCC-teaser:thumb{{size}}.png" } ], "projects_workgroups": [ "d4386" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/", "__class": "Publication" }, { "id": "SCHUETZ-2021-PCC", "type_id": "journalpaper", "tu_id": 300515, "repositum_id": "20.500.12708/58641", "title": "Rendering Point Clouds with Compute Shaders and Vertex Order Optimization", "date": "2021-07-01", "abstract": "While commodity GPUs provide a continuously growing range of features and sophisticated methods for accelerating compute jobs, many state-of-the-art solutions for point cloud rendering still rely on the provided point primitives (GL_POINTS, POINTLIST, ...) of graphics APIs for image synthesis. In this paper, we present several compute-based point cloud rendering approaches that outperform the hardware pipeline by up to an order of magnitude and achieve significantly better frame times than previous compute-based methods. Beyond basic closest-point rendering, we also introduce a fast, high-quality variant to reduce aliasing. We present and evaluate several variants of our proposed methods with different flavors of optimization, in order to ensure their applicability and achieve optimal performance on a range of platforms and architectures with varying support for novel GPU hardware features. During our experiments, the observed peak performance was reached rendering 796 million points (12.7GB) at rates of 62 to 64 frames per second (50 billion points per second, 802GB/s) on an RTX 3090 without the use of level-of-detail structures.\n\nWe further introduce an optimized vertex order for point clouds to boost the efficiency of GL_POINTS by a factor of 5x in cases where hardware rendering is compulsory. We compare different orderings and show that Morton sorted buffers are faster for some viewpoints, while shuffled vertex buffers are faster in others. In contrast, combining both approaches by first sorting according to Morton-code and shuffling the resulting sequence in batches of 128 points leads to a vertex buffer layout with high rendering performance and low sensitivity to viewpoint changes. ", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "fragcount", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1299, "image_height": 985, "name": "SCHUETZ-2021-PCC-fragcount.jpg", "type": "image/jpeg", "size": 836239, "path": "Publication:SCHUETZ-2021-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-fragcount.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-fragcount:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 1650, 193 ], "booktitle": "techreport", "cfp": { "name": "call-for-papers.pdf", "type": "application/pdf", "error": "0", "size": "6107441", "orig_name": "call-for-papers.pdf", "ext": "pdf" }, "date_from": "2021-06-29", "date_to": "2021-07-02", "doi": "10.1111/cgf.14345", "event": "Eurographics Symposium on Rendering 2021 (EGSR '21)", "first_published": "2021-07", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1116 ], "location": "online", "number": "4", "open_access": "yes", "pages": "12", "pages_from": "115", "pages_to": "126", "publisher": "Eurographics Association", "volume": "40", "research_areas": [ "Rendering" ], "keywords": [ "point-based rendering", "compute shader", "real-time rendering" ], "weblinks": [ { "href": "https://github.com/m-schuetz/compute_rasterizer", "caption": "Source Code", "description": null, "main_file": 0 } ], "files": [ { "description": "appendix", "filetitle": "appendix", "main_file": false, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2021-PCC-appendix.pdf", "type": "application/pdf", "size": 5715741, "path": "Publication:SCHUETZ-2021-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-appendix.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-appendix:thumb{{size}}.png" }, { "description": null, "filetitle": "fragcount", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1299, "image_height": 985, "name": "SCHUETZ-2021-PCC-fragcount.jpg", "type": "image/jpeg", "size": 836239, "path": "Publication:SCHUETZ-2021-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-fragcount.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-fragcount:thumb{{size}}.png" }, { "description": "paper", "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2021-PCC-paper.pdf", "type": "application/pdf", "size": 4255515, "path": "Publication:SCHUETZ-2021-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-paper:thumb{{size}}.png" }, { "description": null, "filetitle": "teaser", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 2000, "image_height": 625, "name": "SCHUETZ-2021-PCC-teaser.jpg", "type": "image/jpeg", "size": 722844, "path": "Publication:SCHUETZ-2021-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-teaser.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/SCHUETZ-2021-PCC-teaser:thumb{{size}}.png" } ], "projects_workgroups": [ "d4386", "3DSpatialization" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/", "__class": "Publication" }, { "id": "SCHUETZ-2021-DISS", "type_id": "phdthesis", "tu_id": null, "repositum_id": "20.500.12708/17701", "title": "Interactive Exploration of Point Clouds", "date": "2021-04", "abstract": "Laser scanning, photogrammetry and other 3D scanning approaches generate data sets comprising millions to trillions of points. Modern GPUs can easily render a few million and up to tens of millions of points in real time, but data sets with hundreds of millions of points and more require acceleration structures to be rendered in real time. In this thesis, we present three contributions to the state of the art with the goal of improving the performance as well as the quality of real-time rendered point clouds.\n\nTwo of our contributions address the performance of LOD structure generation. State-of-the-art approaches achieve a throughput of up to around 1 million points per second, which requires users to wait minutes even for smaller data sets with a few hundred million points. Our proposed solutions are: A bottom-up LOD generation approach that creates LOD structures up to an order of magnitude faster than previous work, and a progressive rendering approach that is capable of rendering any point cloud that fits in GPU memory in real time, without the need to generate LOD structures at all. The former achieves a throughput of up to 10 million points per second, and the latter is capable of loading point clouds at rates of up to 37 million points per second from an industry-standard point-cloud format (LAS), and up to 100 million points per second if the file format matches the vertex buffer format. Since it does not need LOD structures, the progressive rendering approach can render already loaded points right away while additional points are still being loaded. \n\nOur third contribution improves the quality of LOD-based point-cloud rendering by introducing a continuous level-of-detail approach that produces gradual transitions in point density, rather than the characteristic and noticeable blocks from discrete LOD structures. It is mainly targeted towards VR applications, where discrete levels of detail are especially noticeable and disturbing, in a large part due to the popping of chunks of points during motion. ", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116 ], "doi": "10.34726/hss.2021.91668", "duration": "5", "open_access": "yes", "pages": "107", "reviewer_1": [ 1855 ], "reviewer_2": [ 1245 ], "rigorosum": "2021-04-07", "supervisor": [ 193 ], "research_areas": [ "Rendering" ], "keywords": [ "point cloud rendering", "lidar" ], "weblinks": [], "files": [ { "description": null, "filetitle": "dissertation", "main_file": false, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2021-DISS-dissertation.pdf", "type": "application/pdf", "size": 4739921, "path": "Publication:SCHUETZ-2021-DISS", "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-DISS/SCHUETZ-2021-DISS-dissertation.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-DISS/SCHUETZ-2021-DISS-dissertation:thumb{{size}}.png" } ], "projects_workgroups": [ "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-DISS/", "__class": "Publication" }, { "id": "SCHUETZ-2020-MPC", "type_id": "journalpaper", "tu_id": null, "repositum_id": "20.500.12708/58254", "title": "Fast Out-of-Core Octree Generation for Massive Point Clouds", "date": "2020-11", "abstract": "We propose an efficient out-of-core octree generation method for arbitrarily large point clouds. It utilizes a hierarchical counting sort to quickly split the point cloud into small chunks, which are then processed in parallel. Levels of detail are generated by subsampling the full data set bottom up using one of multiple exchangeable sampling strategies. We introduce a fast hierarchical approximate blue-noise strategy and compare it to a uniform random sampling strategy. The throughput, including out-of-core access to disk, generating the octree, and writing the final result to disk, is about an order of magnitude faster than the state of the art, and reaches up to around 6 million points per second for the blue-noise approach and up to around 9 million points per second for the uniform random approach on modern SSDs.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 2400, "image_height": 692, "name": "SCHUETZ-2020-MPC-.png", "type": "image/png", "size": 848082, "path": "Publication:SCHUETZ-2020-MPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/SCHUETZ-2020-MPC-.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/SCHUETZ-2020-MPC-:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 948, 193 ], "cfp": { "name": "For Authors - PG2020.pdf", "type": "application/pdf", "error": "0", "size": "909462", "orig_name": "For Authors - PG2020.pdf", "ext": "pdf" }, "date_from": "2021", "date_to": "2021", "doi": "10.1111/cgf.14134", "event": "Pacific Graphics 2020", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1116 ], "location": "Wellington, NZ", "number": "7", "open_access": "yes", "pages": "13", "pages_from": "1", "pages_to": "13", "publisher": "John Wiley & Sons, Inc.", "volume": "39", "research_areas": [ "Rendering" ], "keywords": [ "point clouds", "point-based rendering", "level of detail" ], "weblinks": [ { "href": "https://github.com/potree/PotreeConverter/releases/tag/2.0", "caption": "PotreeConverter 2.0 at github ", "description": "PotreeConverter generates an octree LOD structure for streaming and real-time rendering of massive point clouds. The results can be viewed in web browsers with Potree or as a desktop application with PotreeDesktop.\n\n", "main_file": 0 }, { "href": "https://www.youtube.com/watch?v=g6k-flKWaNI", "caption": "Video", "description": null, "main_file": 0 } ], "files": [ { "description": null, "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 2400, "image_height": 692, "name": "SCHUETZ-2020-MPC-.png", "type": "image/png", "size": 848082, "path": "Publication:SCHUETZ-2020-MPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/SCHUETZ-2020-MPC-.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/SCHUETZ-2020-MPC-:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2020-MPC-paper.pdf", "type": "application/pdf", "size": 25053214, "path": "Publication:SCHUETZ-2020-MPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/SCHUETZ-2020-MPC-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/SCHUETZ-2020-MPC-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "Superhumans" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2020/SCHUETZ-2020-MPC/", "__class": "Publication" }, { "id": "OTEPKA-2020-PPC", "type_id": "journalpaper", "tu_id": null, "repositum_id": null, "title": "Efficient Loading and Visualization of Massive Feature-Richt Point Clouds Without Hierarchical Acceleration Structures", "date": "2020-08", "abstract": "Nowadays, point clouds are the standard product when capturing reality independent of scale and measurement technique. Especially, Dense Image Matching (DIM) and Laser Scanning (LS) are state of the art capturing methods for a great variety of applications producing detailed point clouds up to billions of points. In-depth analysis of such huge point clouds typically requires sophisticated spatial indexing structures to support potentially long-lasting automated non-interactive processing tasks like feature extraction, semantic labelling, surface generation, and the like. Nevertheless, a visual inspection of the point data is often necessary to obtain an impression of the scene, roughly check for completeness, quality, and outlier rates of the captured data in advance. Also intermediate processing results, containing additional per-point computed attributes, may require visual analyses to draw conclusions or to parameterize further processing. Over the last decades a variety of commercial, free, and open source viewers have been developed that can visualise huge point clouds and colorize them based on available attributes. However, they have either a poor loading and navigation performance, visualize only a subset of the points, or require the creation of spatial indexing structures in advance. In this paper, we evaluate a progressive method that is capable of rendering any point cloud that fits in GPU memory in real time without the need of time consuming hierarchical acceleration structure generation. In combination with our multi-threaded LAS and LAZ loaders, we achieve load performance of up to 20 million points per second, display points already while loading, support flexible switching between different attributes, and rendering up to one billion points with visually appealing navigation behaviour. Furthermore, loading times of different data sets for different open source and commercial software packages are analysed.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 521, "image_height": 591, "name": "OTEPKA-2020-PPC-image.jpg", "type": "image/jpeg", "size": 59602, "path": "Publication:OTEPKA-2020-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/OTEPKA-2020-PPC-image.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/OTEPKA-2020-PPC-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1701, 1700, 1116, 1797, 193 ], "cfp": { "name": "isprs-archives-XLIII-B2-2020-1-2020.pdf", "type": "application/pdf", "error": "0", "size": "1916748", "orig_name": "isprs-archives-XLIII-B2-2020-1-2020.pdf", "ext": "pdf" }, "date_from": "2020-08-31", "date_to": "2020-09-02", "doi": "10.5194/isprs-archives-XLIII-B2-2020-293-2020", "event": "XXIV ISPRS Congress (2020 edition)", "issn": "1682-1750", "journal": "ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences", "lecturer": [ 1701 ], "location": "online", "open_access": "yes", "pages_from": "293", "pages_to": "300", "volume": "XLIII-B2-2020", "research_areas": [ "Rendering" ], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 521, "image_height": 591, "name": "OTEPKA-2020-PPC-image.jpg", "type": "image/jpeg", "size": 59602, "path": "Publication:OTEPKA-2020-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/OTEPKA-2020-PPC-image.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/OTEPKA-2020-PPC-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "OTEPKA-2020-PPC-paper.pdf", "type": "application/pdf", "size": 17113367, "path": "Publication:OTEPKA-2020-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/OTEPKA-2020-PPC-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/OTEPKA-2020-PPC-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "External", "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2020/OTEPKA-2020-PPC/", "__class": "Publication" }, { "id": "schuetz-2020-PPC", "type_id": "journalpaper", "tu_id": 291874, "repositum_id": "20.500.12708/58262", "title": "Progressive Real-Time Rendering of One Billion Points Without Hierarchical Acceleration Structures", "date": "2020-05", "abstract": "Research in rendering large point clouds traditionally focused on the generation and use of hierarchical acceleration structures that allow systems to load and render the smallest fraction of the data with the largest impact on the output. The generation of these structures is slow and time consuming, however, and therefore ill-suited for tasks such as quickly looking at scan data stored in widely used unstructured file formats, or to immediately display the results of point-cloud processing tasks.\n\n \nWe propose a progressive method that is capable of rendering any point cloud that fits in GPU memory in real time, without the need to generate hierarchical acceleration structures in advance. Our method supports data sets with a large amount of attributes per point, achieves a load performance of up to 100 million points per second, displays already loaded data in real time while remaining data is still being loaded, and is capable of rendering up to one billion points using an on-the-fly generated shuffled vertex buffer as its data structure, instead of slow-to-generate hierarchical structures. Shuffling is done during loading in order to allow efficiently filling holes with random subsets, which leads to a higher quality convergence behavior. ", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 4061, "image_height": 1183, "name": "schuetz-2020-PPC-.jpg", "type": "image/jpeg", "size": 376597, "path": "Publication:schuetz-2020-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/schuetz-2020-PPC-.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/schuetz-2020-PPC-:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 1700, 1701, 193 ], "booktitle": "EUROGRAPHICS", "cfp": { "name": "EG_2020_call_for_papers.pdf", "type": "application/pdf", "error": "0", "size": "268041", "orig_name": "EG_2020_call_for_papers.pdf", "ext": "pdf" }, "date_from": "2020-05-25", "date_to": "2020-05-29", "doi": "10.1111/cgf.13911", "event": "EUROGRAPHICS 2020", "first_published": "2020-07-13", "issn": "1467-8659", "journal": "Computer Graphics Forum", "lecturer": [ 1116 ], "location": "Norköpping, Sweden", "number": "2", "pages": "14", "pages_from": "51", "pages_to": "64", "publisher": "John Wiley & Sons Ltd.", "volume": "39", "research_areas": [ "Rendering" ], "keywords": [ "point-based rendering" ], "weblinks": [ { "href": "https://github.com/m-schuetz/skye", "caption": "Source Code", "description": null, "main_file": 0 }, { "href": "https://www.youtube.com/watch?v=6_ivIcynok8", "caption": "Video", "description": null, "main_file": 0 } ], "files": [ { "description": null, "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 4061, "image_height": 1183, "name": "schuetz-2020-PPC-.jpg", "type": "image/jpeg", "size": 376597, "path": "Publication:schuetz-2020-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/schuetz-2020-PPC-.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/schuetz-2020-PPC-:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": true, "use_in_gallery": false, "access": "public", "name": "schuetz-2020-PPC-paper.pdf", "type": "application/pdf", "size": 27594913, "path": "Publication:schuetz-2020-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/schuetz-2020-PPC-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/schuetz-2020-PPC-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "Superhumans" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2020/schuetz-2020-PPC/", "__class": "Publication" }, { "id": "SCHUETZ-2019-PCC", "type_id": "poster", "tu_id": null, "repositum_id": null, "title": "Rendering Point Clouds with Compute Shaders", "date": "2019-11", "abstract": "We propose a compute shader based point cloud rasterizer with up to 10 times higher performance than classic point-based rendering with the GL_POINT primitive. In addition to that, our rasterizer offers 5 byte depth-buffer precision with uniform or customizable distribution, and we show that it is possible to implement a highquality splatting method that blends together overlapping fragments while still maintaining higher frame-rates than the traditional approach.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1145, "image_height": 445, "name": "SCHUETZ-2019-PCC-image.png", "type": "image/png", "size": 90952, "path": "Publication:SCHUETZ-2019-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 193 ], "cfp": { "name": "cfp_siggraph_asia2019.pdf", "type": "application/pdf", "error": "0", "size": "715388", "orig_name": "cfp_siggraph_asia2019.pdf", "ext": "pdf" }, "date_from": "2019-11", "date_to": "2019-11", "event": "SIGGRAPH Asia", "isbn": "978-1-4503-6943-5/19/11", "research_areas": [ "Rendering" ], "keywords": [], "weblinks": [ { "href": "https://github.com/m-schuetz/compute_rasterizer", "caption": "source", "description": null, "main_file": 0 } ], "files": [ { "description": null, "filetitle": "abstract", "main_file": false, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2019-PCC-abstract.pdf", "type": "application/pdf", "size": 487892, "path": "Publication:SCHUETZ-2019-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-abstract.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-abstract:thumb{{size}}.png" }, { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 1145, "image_height": 445, "name": "SCHUETZ-2019-PCC-image.png", "type": "image/png", "size": 90952, "path": "Publication:SCHUETZ-2019-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-image:thumb{{size}}.png" }, { "description": null, "filetitle": "poster", "main_file": false, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2019-PCC-poster.pdf", "type": "application/pdf", "size": 15302985, "path": "Publication:SCHUETZ-2019-PCC", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-poster.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/SCHUETZ-2019-PCC-poster:thumb{{size}}.png" } ], "projects_workgroups": [], "url": "https://www.cg.tuwien.ac.at/research/publications/2019/SCHUETZ-2019-PCC/", "__class": "Publication" }, { "id": "schuetz-2019-LCO", "type_id": "poster", "tu_id": 283339, "repositum_id": null, "title": "Live Coding of a VR Render Engine in VR", "date": "2019-03-27", "abstract": "Live coding in virtual reality allows users to create and modify their surroundings through code without the need to leave the virtual reality environment. Previous work focuses on modifying the scene. We propose an application that allows developers to modify virtually everything at runtime, including the scene but also the render engine, shader code and input handling, using standard desktop IDEs through a desktop mirror.\n", "authors_et_al": false, "substitute": null, "main_image": { "description": "Modifying brush generation and rendering code at runtime in VR.", "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1006, "image_height": 743, "name": "schuetz-2019-LCO-.png", "type": "image/png", "size": 460185, "path": "Publication:schuetz-2019-LCO", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 193 ], "address": "http://ieeevr.org/2019/", "cfp": { "name": "cfposters_ieeevr_2019.pdf", "type": "application/pdf", "error": "0", "size": "516102", "orig_name": "cfposters_ieeevr_2019.pdf", "ext": "pdf" }, "date_from": "2019-03", "date_to": "2019-03", "doi": "https://doi.org/10.1109/VR.2019.8797760", "event": "IEEE VR 2019", "location": "Osaka", "pages_from": "1150", "pages_to": "1151", "publisher": "IEEE", "research_areas": [ "Rendering" ], "keywords": [ "virtual reality", "live coding", "VR" ], "weblinks": [ { "href": "https://github.com/m-schuetz/Fenek", "caption": null, "description": null, "main_file": 0 } ], "files": [ { "description": "Modifying brush generation and rendering code at runtime in VR.", "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1006, "image_height": 743, "name": "schuetz-2019-LCO-.png", "type": "image/png", "size": 460185, "path": "Publication:schuetz-2019-LCO", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-:thumb{{size}}.png" }, { "description": "Two page poster abstract", "filetitle": "poster_abstract", "main_file": false, "use_in_gallery": false, "access": "public", "name": "schuetz-2019-LCO-poster_abstract.pdf", "type": "application/pdf", "size": 1554925, "path": "Publication:schuetz-2019-LCO", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-poster_abstract.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-poster_abstract:thumb{{size}}.png" }, { "description": null, "filetitle": "poster", "main_file": false, "use_in_gallery": false, "access": "public", "name": "schuetz-2019-LCO-poster.pdf", "type": "application/pdf", "size": 13220664, "path": "Publication:schuetz-2019-LCO", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-poster.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/schuetz-2019-LCO-poster:thumb{{size}}.png" } ], "projects_workgroups": [ "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-LCO/", "__class": "Publication" }, { "id": "schuetz-2019-CLOD", "type_id": "inproceedings", "tu_id": 283354, "repositum_id": null, "title": "Real-Time Continuous Level of Detail Rendering of Point Clouds", "date": "2019-03", "abstract": "Real-time rendering of large point clouds requires acceleration structures that reduce the number of points drawn on screen. State-of-the art algorithms group and render points in hierarchically organized chunks with varying extent and density, which results in sudden changes of density from one level of detail to another, as well as noticeable popping artifacts when additional chunks are blended in or out. \nThese popping artifacts are especially noticeable at lower levels of detail, and consequently in virtual reality, where high performance requirements impose a reduction in detail.\n\nWe propose a continuous level-of-detail method that exhibits gradual rather than sudden changes in density. Our method continuously recreates a down-sampled vertex buffer from the full point cloud, based on camera orientation, position, and distance to the camera, in a point-wise rather than chunk-wise fashion and at speeds up to 17 million points per millisecond.\nAs a result, additional details are blended in or out in a less noticeable and significantly less irritating manner as compared to the state of the art. The improved acceptance of our method was successfully evaluated in a user study.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "screenshot_1", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 961, "image_height": 878, "name": "schuetz-2019-CLOD-screenshot_1.png", "type": "image/png", "size": 870310, "path": "Publication:schuetz-2019-CLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-screenshot_1.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-screenshot_1:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 1030, 193 ], "booktitle": "2019 IEEE Conference on Virtual Reality and 3D User Interfaces", "cfp": { "name": "cfpapers_ieeevr_2019.pdf", "type": "application/pdf", "error": "0", "size": "829256", "orig_name": "cfpapers_ieeevr_2019.pdf", "ext": "pdf" }, "date_from": "2019-03-23", "date_to": "2019-03-27", "doi": "10.1109/VR.2019.8798284", "event": "IEEE VR 2019, the 26th IEEE Conference on Virtual Reality and 3D User Interfaces", "lecturer": [ 1116 ], "location": "Osaka, Japan", "pages_from": "103", "pages_to": "110", "publisher": "IEEE", "research_areas": [ "Rendering" ], "keywords": [ "point clouds, virtual reality, VR" ], "weblinks": [ { "href": "https://github.com/m-schuetz/ieeevr_2019_clod", "caption": "Essential source code samples", "description": null, "main_file": 0 } ], "files": [ { "description": "continuous LOD subsample selected for the users current viewpoint", "filetitle": "birds_eye", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1494, "image_height": 1221, "name": "schuetz-2019-CLOD-birds_eye.png", "type": "image/png", "size": 2051540, "path": "Publication:schuetz-2019-CLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-birds_eye.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-birds_eye:thumb{{size}}.png" }, { "description": "More uniform distribution of points in screen space, compared to staircase artifacts from discrete LOD methods.", "filetitle": "distribution", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 498, "image_height": 228, "name": "schuetz-2019-CLOD-distribution.png", "type": "image/png", "size": 94654, "path": "Publication:schuetz-2019-CLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-distribution.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-distribution:thumb{{size}}.png" }, { "description": null, "filetitle": "paper_preprint", "main_file": false, "use_in_gallery": false, "access": "public", "name": "schuetz-2019-CLOD-paper_preprint.pdf", "type": "application/pdf", "size": 15684243, "path": "Publication:schuetz-2019-CLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-paper_preprint.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-paper_preprint:thumb{{size}}.png" }, { "description": null, "filetitle": "screenshot_1", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 961, "image_height": 878, "name": "schuetz-2019-CLOD-screenshot_1.png", "type": "image/png", "size": 870310, "path": "Publication:schuetz-2019-CLOD", "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-screenshot_1.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/schuetz-2019-CLOD-screenshot_1:thumb{{size}}.png" } ], "projects_workgroups": [ "rend", "VRVis" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2019/schuetz-2019-CLOD/", "__class": "Publication" }, { "id": "schuetz-2018-PPC", "type_id": "poster", "tu_id": null, "repositum_id": null, "title": "Progressive Real-Time Rendering of Unprocessed Point Clouds", "date": "2018-08", "abstract": "Rendering tens of millions of points in real time usually requires either high-end \ngraphics cards, or the use of spatial acceleration structures. \nWe introduce a method to progressively display as many points as the GPU memory can hold in real time \nby reprojecting what was visible and randomly adding additional points to uniformly \nconverge towards the full result within a few frames. \n\nOur method heavily limits the number of points that have to be rendered each frame and \nit converges quickly and in a visually pleasing way, which makes it suitable even \nfor notebooks with low-end GPUs. \nThe data structure consists of a randomly shuffled array of points that is incrementally generated \non-the-fly while points are being loaded. \n\nDue to this, it can be used to directly view point clouds in common sequential formats such as LAS or LAZ while they are being loaded and without the need to generate spatial acceleration structures in advance, as long as the data fits into GPU memory.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1213, "image_height": 662, "name": "schuetz-2018-PPC-.png", "type": "image/png", "size": 1023977, "path": "Publication:schuetz-2018-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 193 ], "cfp": { "name": "call_for_posters.pdf", "type": "application/pdf", "error": "0", "size": "630843", "orig_name": "call_for_posters.pdf", "ext": "pdf" }, "date_from": "2018-08-12", "date_to": "2018-08-16", "doi": "10.1145/3230744.3230816", "event": "ACM SIGGRAPH 2018", "isbn": "978-1-4503-5817-0/18/08", "location": "Vancouver, Canada", "pages_from": "Article 41", "publisher": "ACM", "research_areas": [ "Rendering" ], "keywords": [ "point based rendering, point cloud, LIDAR" ], "weblinks": [], "files": [ { "description": null, "filetitle": "", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1213, "image_height": 662, "name": "schuetz-2018-PPC-.png", "type": "image/png", "size": 1023977, "path": "Publication:schuetz-2018-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-:thumb{{size}}.png" }, { "description": null, "filetitle": "abstract", "main_file": true, "use_in_gallery": false, "access": "public", "name": "schuetz-2018-PPC-abstract.pdf", "type": "application/pdf", "size": 1041710, "path": "Publication:schuetz-2018-PPC", "url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-abstract.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-abstract:thumb{{size}}.png" }, { "description": null, "filetitle": "poster", "main_file": true, "use_in_gallery": false, "access": "public", "preview_image_width": 1200, "preview_image_height": 857, "name": "schuetz-2018-PPC-poster.pdf", "type": "application/pdf", "size": 21784835, "path": "Publication:schuetz-2018-PPC", "preview_name": "schuetz-2018-PPC-poster:preview.png", "preview_type": "image/png", "preview_size": 582932, "url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-poster.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/schuetz-2018-PPC-poster:thumb{{size}}.png" } ], "projects_workgroups": [ "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2018/schuetz-2018-PPC/", "__class": "Publication" }, { "id": "kroesl_x_card_2017", "type_id": "xmascard", "tu_id": null, "repositum_id": null, "title": "X-Mas Card 2017", "date": "2017-12", "abstract": "This Christmas we want to illuminate your holidays with luminaires specifically designed for this occasion. The festive scene on this card features semi-translucent luminaires in the shape of christmas trees. The light distribution of the corresponding luminaire model was simulated in LiteMaker,an interactive luminaire development tool that was developed at TU Wien and VRVis. LiteMaker provides interactive editing functionality and very fast high-quality previews of the final physically correct simulated light distribution of a luminaire model. The final scene and light distributions were rendered using our light­\nplanning software HILITE.\n\nDie weihnachtliche Szene auf dieser Karte wird durch Leuchten in Form von Christbäumen erhellt. Für das Lichtdesign der Szene wurde LiteMaker verwendet, ein an der TU Wien und am VRVis entwickeltes interaktives Entwicklungswerkzeug fur Beleuchtungskörper. Durch interaktives Bearbeiten, und sehr schnelle aber dennoch hochwertige physikalisch korrekte Vorschaubilder, ermöglicht LiteMaker ein rascheres Design von Beleuchtungskonzepten. Die fertige Szene wurde anschließend in unserer Lichtsimuationssoftware HILITE gerendert.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "X max 2017", "main_file": true, "use_in_gallery": true, "access": "public", "image_width": 1030, "image_height": 730, "name": "kroesl_x_card_2017-X max 2017.JPG", "type": "image/jpeg", "size": 83593, "path": "Publication:kroesl_x_card_2017", "url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/kroesl_x_card_2017-X max 2017.JPG", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/kroesl_x_card_2017-X max 2017:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1030, 1116 ], "research_areas": [ "IllVis" ], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "X Mas card", "main_file": true, "use_in_gallery": false, "access": "public", "name": "kroesl_x_card_2017-X Mas card.pdf", "type": "application/pdf", "size": 998745, "path": "Publication:kroesl_x_card_2017", "url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/kroesl_x_card_2017-X Mas card.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/kroesl_x_card_2017-X Mas card:thumb{{size}}.png" }, { "description": null, "filetitle": "X max 2017", "main_file": true, "use_in_gallery": true, "access": "public", "image_width": 1030, "image_height": 730, "name": "kroesl_x_card_2017-X max 2017.JPG", "type": "image/jpeg", "size": 83593, "path": "Publication:kroesl_x_card_2017", "url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/kroesl_x_card_2017-X max 2017.JPG", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/kroesl_x_card_2017-X max 2017:thumb{{size}}.png" } ], "projects_workgroups": [ "xmas" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2017/kroesl_x_card_2017/", "__class": "Publication" }, { "id": "SCHUETZ-2016-POT", "type_id": "masterthesis", "tu_id": null, "repositum_id": null, "title": "Potree: Rendering Large Point Clouds in Web Browsers", "date": "2016-09-19", "abstract": "This thesis introduces Potree, a web-based renderer for large point clouds. It allows users\nto view data sets with billions of points, from sources such as LIDAR or photogrammetry,\nin real time in standard web browsers.\nOne of the main advantages of point cloud visualization in web browser is that it\nallows users to share their data sets with clients or the public without the need to install\nthird-party applications and transfer huge amounts of data in advance. The focus on\nlarge point clouds, and a variety of measuring tools, also allows users to use Potree to\nlook at, analyze and validate raw point cloud data, without the need for a time-intensive\nand potentially costly meshing step.\nThe streaming and rendering of billions of points in web browsers, without the need\nto load large amounts of data in advance, is achieved with a hierarchical structure that\nstores subsamples of the original data at different resolutions. A low resolution is stored\nin the root node and with each level, the resolution gradually increases. The structure\nallows Potree to cull regions of the point cloud that are outside the view frustum, and\nto render distant regions at a lower level of detail.\nThe result is an open source point cloud viewer, which was able to render point cloud\ndata sets of up to 597 billion points, roughly 1.6 terabytes after compression, in real time\nin a web browser.", "authors_et_al": false, "substitute": null, "main_image": { "description": "Around 280 million points.\nPoint cloud courtesy of Pix4D.", "filetitle": "Matterhorn", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 906, "image_height": 741, "name": "SCHUETZ-2016-POT-Matterhorn.png", "type": "image/png", "size": 989456, "path": "Publication:SCHUETZ-2016-POT", "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-Matterhorn.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-Matterhorn:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116 ], "date_end": "2016-09-10", "date_start": "2014-08-01", "matrikelnr": "0825723", "supervisor": [ 193 ], "research_areas": [ "Rendering" ], "keywords": [ "point cloud rendering", "WebGL", "LIDAR" ], "weblinks": [ { "href": "https://github.com/potree", "caption": "github repository", "description": null, "main_file": 0 } ], "files": [ { "description": "Around 17 billion points. \nPoint cloud courtesy of Open Topography and PG&E.", "filetitle": " San Luis Obispo County coast", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 2000, "image_height": 990, "name": "SCHUETZ-2016-POT- San Luis Obispo County coast.jpg", "type": "image/jpeg", "size": 386647, "path": "Publication:SCHUETZ-2016-POT", "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT- San Luis Obispo County coast.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT- San Luis Obispo County coast:thumb{{size}}.png" }, { "description": "Around 280 million points.\nPoint cloud courtesy of Pix4D.", "filetitle": "Matterhorn", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 906, "image_height": 741, "name": "SCHUETZ-2016-POT-Matterhorn.png", "type": "image/png", "size": 989456, "path": "Publication:SCHUETZ-2016-POT", "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-Matterhorn.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-Matterhorn:thumb{{size}}.png" }, { "description": null, "filetitle": "poster", "main_file": true, "use_in_gallery": false, "access": "public", "preview_image_width": null, "preview_image_height": null, "name": "SCHUETZ-2016-POT-poster.pdf", "type": "application/pdf", "size": 18316148, "path": "Publication:SCHUETZ-2016-POT", "preview_name": "SCHUETZ-2016-POT-poster:preview.png", "preview_type": null, "preview_size": null, "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-poster.pdf", "thumb_image_sizes": [] }, { "description": "Point cloud courtesy of Riegl.", "filetitle": "Retz", "main_file": false, "use_in_gallery": false, "access": "public", "image_width": 866, "image_height": 533, "name": "SCHUETZ-2016-POT-Retz.png", "type": "image/png", "size": 952898, "path": "Publication:SCHUETZ-2016-POT", "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-Retz.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-Retz:thumb{{size}}.png" }, { "description": null, "filetitle": "thesis", "main_file": true, "use_in_gallery": false, "access": "public", "preview_image_width": 906, "preview_image_height": 741, "name": "SCHUETZ-2016-POT-thesis.pdf", "type": "application/pdf", "size": 95787159, "path": "Publication:SCHUETZ-2016-POT", "preview_name": "SCHUETZ-2016-POT-thesis:preview.png", "preview_type": "image/png", "preview_size": 989456, "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-thesis.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/SCHUETZ-2016-POT-thesis:thumb{{size}}.png" } ], "projects_workgroups": [ "Harvest4D" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2016/SCHUETZ-2016-POT/", "__class": "Publication" }, { "id": "Martinez-2015-TTB", "type_id": "inproceedings", "tu_id": null, "repositum_id": null, "title": "Taming the beast: Free and open-source massive point cloud web visualization", "date": "2015-11", "abstract": "Powered by WebGL, some renderers have recently become available for the visualization of point cloud data over the web, for example Plasio or Potree. We have extended Potree to be able to visualize massive point clouds and we have successfully used it with the second national Lidar survey of the Netherlands, AHN2, with 640 billion points. In addition to the visualization, the publicly available service at ttp://ahn2.pointclouds.nl/ also features a multi-resolution download tool, a geographic name search bar, a measurement toolkit, a 2D orientation map with field of view depiction, a demo mode and the tuning of the visualization parameters. Potree relies on reorganizing the point cloud data into an multi-resolution octree data structure. However, this reorganization is very time consuming for massive data sets. Hence, we have used a divide and conquer approach to decrease the octree creation time. To achieve such performance improvement we divided the entire space into smaller cells, generated an octree for each of them in a distributed manner and then we merged them into a single massive octree. The merging is possible because the extent of all the nodes of the octrees is known and fixed. All the developed tools are free and open-source (FOSS) and they can be used to visualize over the web other massive point clouds.\n\n", "authors_et_al": false, "substitute": null, "main_image": null, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 5356, 5357, 5358, 1116, 5359, 5360, 5361 ], "booktitle": "Capturing Reality Forum", "date_from": "2015", "date_to": "2015", "event": "Capturing Reality Forum", "lecturer": [ 5356 ], "pages_from": "1", "pages_to": "1", "research_areas": [], "keywords": [], "weblinks": [], "files": [ { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1050, "image_height": 589, "name": "Martinez-2015-TTB-image.jpg", "type": "image/jpeg", "size": 96671, "path": "Publication:Martinez-2015-TTB", "url": "https://www.cg.tuwien.ac.at/research/publications/2015/Martinez-2015-TTB/Martinez-2015-TTB-image.jpg", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2015/Martinez-2015-TTB/Martinez-2015-TTB-image:thumb{{size}}.png" }, { "description": null, "filetitle": "paper", "main_file": false, "use_in_gallery": false, "access": "public", "name": "Martinez-2015-TTB-paper.pdf", "type": "application/pdf", "size": 11189274, "path": "Publication:Martinez-2015-TTB", "url": "https://www.cg.tuwien.ac.at/research/publications/2015/Martinez-2015-TTB/Martinez-2015-TTB-paper.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2015/Martinez-2015-TTB/Martinez-2015-TTB-paper:thumb{{size}}.png" } ], "projects_workgroups": [ "rend" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2015/Martinez-2015-TTB/", "__class": "Publication" }, { "id": "SCHUETZ-2015-HQP", "type_id": "inproceedings", "tu_id": null, "repositum_id": null, "title": "High-Quality Point Based Rendering Using Fast Single Pass Interpolation", "date": "2015-09", "abstract": "We present a method to improve the visual quality of point cloud renderings through a nearest-neighbor-like interpolation of points. This allows applications to render points at larger sizes in order to reduce holes, without reducing the readability of fine details due to occluding points. The implementation requires only few modifications to existing shaders, making it eligible to be integrated in software applications without major design changes.", "authors_et_al": false, "substitute": null, "main_image": { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1000, "image_height": 1000, "name": "SCHUETZ-2015-HQP-image.png", "type": "image/png", "size": 1123770, "path": "Publication:SCHUETZ-2015-HQP", "url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/SCHUETZ-2015-HQP-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/SCHUETZ-2015-HQP-image:thumb{{size}}.png" }, "sync_repositum_override": null, "repositum_presentation_id": null, "authors": [ 1116, 193 ], "booktitle": "Proceedings of Digital Heritage 2015 Short Papers", "date_from": "2015-09-28", "date_to": "2015-10-02", "lecturer": [ 1116 ], "location": "Granada, Spain", "pages_from": "369", "pages_to": "372", "research_areas": [ "Rendering" ], "keywords": [ "point-based rendering" ], "weblinks": [], "files": [ { "description": null, "filetitle": "draft", "main_file": true, "use_in_gallery": false, "access": "public", "name": "SCHUETZ-2015-HQP-draft.pdf", "type": "application/pdf", "size": 1754449, "path": "Publication:SCHUETZ-2015-HQP", "url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/SCHUETZ-2015-HQP-draft.pdf", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/SCHUETZ-2015-HQP-draft:thumb{{size}}.png" }, { "description": null, "filetitle": "image", "main_file": false, "use_in_gallery": true, "access": "public", "image_width": 1000, "image_height": 1000, "name": "SCHUETZ-2015-HQP-image.png", "type": "image/png", "size": 1123770, "path": "Publication:SCHUETZ-2015-HQP", "url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/SCHUETZ-2015-HQP-image.png", "thumb_image_sizes": [ 16, 64, 100, 175, 300, 600 ], "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/SCHUETZ-2015-HQP-image:thumb{{size}}.png" } ], "projects_workgroups": [ "Harvest4D" ], "url": "https://www.cg.tuwien.ac.at/research/publications/2015/SCHUETZ-2015-HQP/", "__class": "Publication" } ]