@article{hladky-2022-QS, title = "QuadStream: A Quad-Based Scene Streaming Architecture for Novel Viewpoint Reconstruction", author = "Jozef Hladky and Michael Stengel and Nicholas Vining and Bernhard Kerbl and Hans-Peter Seidel and Markus Steinberger", year = "2022", abstract = "Cloud rendering is attractive when targeting thin client devices such as phones or VR/AR headsets, or any situation where a high-end GPU is not available due to thermal or power constraints. However, it introduces the challenge of streaming rendered data over a network in a manner that is robust to latency and potential dropouts. Current approaches range from streaming transmitted video and correcting it on the client---which fails in the presence of disocclusion events---to solutions where the server sends geometry and all rendering is performed on the client. To balance the competing goals of disocclusion robustness and minimal client workload, we introduce QuadStream, a new streaming technique that reduces motion-to-photon latency by allowing clients to render novel views on the fly and is robust against disocclusions. Our key idea is to transmit an approximate geometric scene representation to the client which is independent of the source geometry and can render both the current view frame and nearby adjacent views. Motivated by traditional macroblock approaches to video codec design, we decompose the scene seen from positions in a view cell into a series of view-aligned quads from multiple views, or QuadProxies. By operating on a rasterized G-Buffer, our approach is independent of the representation used for the scene itself. Our technical contributions are an efficient parallel quad generation, merging, and packing strategy for proxy views that cover potential client movement in a scene; a packing and encoding strategy allowing masked quads with depth information to be transmitted as a frame coherent stream; and an efficient rendering approach that takes advantage of modern hardware capabilities to turn our QuadStream representation into complete novel views on thin clients. According to our experiments, our approach achieves superior quality compared both to streaming methods that rely on simple video data and to geometry-based streaming.", month = dec, journal = "ACM Transactions on Graphics", volume = "41", number = "6", issn = "1557-7368", publisher = "ASSOC COMPUTING MACHINERY", keywords = "streaming, real-time rendering, virtual reality", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/hladky-2022-QS/", } @article{SCHUETZ-2022-PCC, title = "Software Rasterization of 2 Billion Points in Real Time", author = "Markus Sch\"{u}tz and Bernhard Kerbl and Michael Wimmer", year = "2022", 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. ", month = jul, journal = "Proceedings of the ACM on Computer Graphics and Interactive Techniques", volume = "5", number = "3", issn = "2577-6193", doi = "10.1145/3543863", pages = "1--17", keywords = "point-based rendering", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/SCHUETZ-2022-PCC/", } @article{cardoso-2022-rtpercept, title = "Training and Predicting Visual Error for Real-Time Applications", author = "Joao Afonso Cardoso and Bernhard Kerbl and Lei Yang and Yury Uralsky and Michael Wimmer", year = "2022", abstract = "Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase performance and improve efficiency. A wide range of different metrics has been established, with the most sophisticated being capable of capturing the perceptual characteristics of the human visual system. However, their complexity, computational expense, and reliance on reference images to compare against prevent their generalized use in real-time, restricting such applications to using only the simplest available metrics. In this work, we explore the abilities of convolutional neural networks to predict a variety of visual metrics without requiring either reference or rendered images. Specifically, we train and deploy a neural network to estimate the visual error resulting from reusing shading or using reduced shading rates. The resulting models account for 70%--90% of the variance while achieving up to an order of magnitude faster computation times. Our solution combines image-space information that is readily available in most state-of-the-art deferred shading pipelines with reprojection from previous frames to enable an adequate estimate of visual errors, even in previously unseen regions. We describe a suitable convolutional network architecture and considerations for data preparation for training. We demonstrate the capability of our network to predict complex error metrics at interactive rates in a real-time application that implements content-adaptive shading in a deferred pipeline. Depending on the portion of unseen image regions, our approach can achieve up to 2x performance compared to state-of-the-art methods.", month = may, journal = "Proceedings of the ACM on Computer Graphics and Interactive Techniques", volume = "5", number = "1", issn = "2577-6193", doi = "10.1145/3522625", pages = "17", publisher = "Association for Computing Machinery", pages = "1--17", keywords = "perceptual error, variable rate shading, real-time", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/", } @inproceedings{celarek-2022-gmcn, title = "Gaussian Mixture Convolution Networks", author = "Adam Celarek and Pedro Hermosilla-Casajus and Bernhard Kerbl and Timo Ropinski and Michael Wimmer", year = "2022", abstract = "This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures. In contrast to tensors, these do not suffer from the curse of dimensionality and allow for a compact representation, as data is only stored where details exist. Convolution kernels and data are Gaussian mixtures with unconstrained weights, positions, and covariance matrices. Similar to discrete convolutional networks, each convolution step produces several feature channels, represented by independent Gaussian mixtures. Since traditional transfer functions like ReLUs do not produce Gaussian mixtures, we propose using a fitting of these functions instead. This fitting step also acts as a pooling layer if the number of Gaussian components is reduced appropriately. We demonstrate that networks based on this architecture reach competitive accuracy on Gaussian mixtures fitted to the MNIST and ModelNet data sets.", month = apr, publisher = "OpenReview.org", event = "ICLR | 2022", booktitle = "The Tenth International Conference on Learning Representations (ICLR 2022)", pages = "1--23", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/celarek-2022-gmcn/", } @inproceedings{unterguggenberger-2022-vulkan, title = "The Road to Vulkan: Teaching Modern Low-Level APIs in Introductory Graphics Courses", author = "Johannes Unterguggenberger and Bernhard Kerbl and Michael Wimmer", year = "2022", abstract = "For over two decades, the OpenGL API provided users with the means for implementing versatile, feature-rich, and portable real-time graphics applications. Consequently, it has been widely adopted by practitioners and educators alike and is deeply ingrained in many curricula that teach real-time graphics for higher education. Over the years, the architecture of graphics processing units (GPUs) incrementally diverged from OpenGL's conceptual design. The more recently introduced Vulkan API provides a more modern, fine-grained approach for interfacing with the GPU. Various properties of this API and overall trends suggest that Vulkan could soon replace OpenGL in many areas. Hence, it stands to reason that educators who have their students' best interests at heart should provide them with corresponding lecture material. However, Vulkan is notoriously verbose and rather challenging for first-time users, thus transitioning to this new API bears a considerable risk of failing to achieve expected teaching goals. In this paper, we document our experiences after teaching Vulkan in an introductory graphics course side-by-side with conventional OpenGL. A final survey enables us to draw conclusions about perceived workload, difficulty, and students' acceptance of either approach and identify suitable conditions and recommendations for teaching Vulkan to undergraduate students.", month = apr, isbn = "978-3-03868-170-0", publisher = "The Eurographics Association", location = "Reims", issn = "1017-4656", event = "Eurographics 2022", doi = "10.2312/eged.20221043", booktitle = "Eurographics 2022 - Education Papers", pages = "9", pages = "31--39", keywords = "vulkan, gpu, opengl", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/unterguggenberger-2022-vulkan/", } @inproceedings{kerbl-2022-trienc, title = "An Improved Triangle Encoding Scheme for Cached Tessellation", author = "Bernhard Kerbl and Linus Horvath and Daniel Cornel and Michael Wimmer", year = "2022", abstract = "With the recent advances in real-time rendering that were achieved by embracing software rasterization, the interest in alternative solutions for other fixed-function pipeline stages rises. In this paper, we revisit a recently presented software approach for cached tessellation, which compactly encodes and stores triangles in GPU memory. While the proposed technique is both efficient and versatile, we show that the original encoding is suboptimal and provide an alternative scheme that acts as a drop-in replacement. As shown in our evaluation, the proposed modifications can yield performance gains of 40\% and more.", month = apr, isbn = "978-3-03868-169-4", location = "Reims", issn = "1017-4656", event = "Eurographics 2022", editor = "Pelechano, Nuria and Vanderhaeghe, David", doi = "10.2312/egs.20221031", booktitle = "Eurographics 2022 - Short Papers", pages = "1--4", keywords = "gpu, real-time, tessellation", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/kerbl-2022-trienc/", } @inproceedings{kerbl-2022-cuda, title = "CUDA and Applications to Task-based Programming", author = "Bernhard Kerbl and Michael Kenzel and Martin Winter and Markus Steinberger", year = "2022", abstract = "To provide a profound understanding of how CUDA applications can achieve peak performance, the first two parts of this tutorial outline the modern CUDA architecture. Following a basic introduction, we expose how language features are linked to---and constrained by---the underlying physical hardware components. Furthermore, we describe common applications for massively parallel programming, offer a detailed breakdown of potential issues, and list ways to mitigate performance impacts. An exemplary analysis of PTX and SASS snippets illustrates how code patterns in CUDA are mapped to actual hardware instructions. In parts 3 and 4, we focus on novel features that were enabled by the arrival of CUDA 10+ toolkits and the Volta+ architectures, such as ITS, tensor cores, and the graph API. In addition to basic use case demonstrations, we outline our own experiences with these capabilities and their potential performance benefits. We also discuss how long-standing best practices are affected by these changes and describe common caveats for dealing with legacy code on recent GPU models. We show how these considerations can be implemented in practice by presenting state-of-the-art research into task-based GPU scheduling, and how the dynamic adjustment of thread roles and group configurations can significantly increase performance.", month = apr, booktitle = "Eurographics 2022 - Tutorials", editor = "Stefanie Hahmann and Gustavo Patow", location = "Reims", publisher = "The Eurographics Association", keywords = "Parallel Programming, GPU", URL = "https://www.cg.tuwien.ac.at/research/publications/2022/kerbl-2022-cuda/", } @inproceedings{murturi_PGG, title = "On Provisioning Procedural Geometry Workloads on Edge Architectures", author = "Ilir Murturi and Chao Jia and Bernhard Kerbl and Michael Wimmer and Schahram Dustdar and Christos Tsigkanos", year = "2021", abstract = "Contemporary applications such as those within Augmented or Virtual Reality (AR/VR) pose challenges for software architectures supporting them, which have to adhere to stringent latency, data transmission, and performance requirements. This manifests in processing 3D models, whose 3D contents are increasingly generated procedurally rather than explicitly, resulting in computational workloads (i.e., perceived as Procedural Geometry Workloads) with particular characteristics and resource requirements. Traditionally, executing such workloads takes place in resource-rich environments such as the cloud. However, the massive amount of data transfer, heterogeneous devices, and networks involved affect latency, which in turn causes low-quality visualization in user-facing applications (e.g., AR/VR). To overcome such challenges, processing elements available close to end users can be leveraged to generate 3D models instead, and as such the edge emerges as a central architectural entity. This paper describes such procedural geometry workloads, their particular characteristics, and challenges to execute them on heterogeneous devices. Furthermore, we propose an architecture capable of provisioning procedural geometry workloads in edge scenarios.", month = oct, isbn = "978-989-758-536-4", publisher = "SciTePress", organization = "INSTICC", event = "17th International Conference on Web Information Systems and Technologies - WEBIST", editor = " Francisco Dom\'{i}nguez Mayo, Massimo Marchiori and Joaquim Filipe", doi = "10.5220/0010687800003058", booktitle = "Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST", pages = "6", pages = "354--359", keywords = "distributed systems, procedural geometry, rendering", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/murturi_PGG/", } @inproceedings{roth_vdi, title = "View-Dependent Impostors for Architectural Shape Grammars", author = "Chao Jia and Moritz Roth and Bernhard Kerbl and Michael Wimmer", year = "2021", abstract = "Procedural generation has become a key component in satisfying a growing demand for ever-larger, highly detailed geometry in realistic, open-world games and simulations. In this paper, we present our work towards a new level-of-detail mechanism for procedural geometry shape grammars. Our approach automatically identifies and adds suitable surrogate rules to a shape grammar's derivation tree. Opportunities for surrogates are detected in a dedicated pre-processing stage. Where suitable, textured impostors are then used for rendering based on the current viewpoint at runtime. Our proposed methods generate simplified geometry with superior visual quality to the state-of-the-art and roughly the same rendering performance.", month = oct, isbn = "978-3-03868-162-5", publisher = "Eurographics Association", organization = "The Eurographics Association", location = "online", event = "Pacific Graphics 2021", editor = "Lee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and W\"{u}nsche, Burkhard", doi = "10.2312/pg.20211390", booktitle = "Pacific Graphics Short Papers, Posters, and Work-in-Progress Papers", pages = "2", pages = "63--64", keywords = "procedural geometry, real-time, GPU", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/roth_vdi/", } @inproceedings{stappen_SteFAS, title = "Temporally Stable Content-Adaptive and Spatio-Temporal Shading Rate Assignment for Real-Time Applications", author = "Stefan Stappen and Johannes Unterguggenberger and Bernhard Kerbl and Michael Wimmer", year = "2021", abstract = "We propose two novel methods to improve the efficiency and quality of real-time rendering applications: Texel differential-based content-adaptive shading (TDCAS) and spatio-temporally filtered adaptive shading (STeFAS). Utilizing Variable Rate Shading (VRS)-a hardware feature introduced with NVIDIA's Turing micro-architecture-and properties derived during rendering or Temporal Anti-Aliasing (TAA), our techniques adapt the resolution to improve the performance and quality of real-time applications. VRS enables different shading resolution for different regions of the screen during a single render pass. In contrast to other techniques, TDCAS and STeFAS have very little overhead for computing the shading rate. STeFAS enables up to 4x higher rendering resolutions for similar frame rates, or a performance increase of 4× at the same resolution.", month = oct, isbn = "978-3-03868-162-5", publisher = "Eurographics Association", organization = "The Eurographics Association", location = "online", event = "Pacific Graphics 2021", editor = "Lee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and W\"{u}nsche, Burkhard", doi = "10.2312/pg.20211391", booktitle = "Pacific Graphics Short Papers, Posters, and Work-in-Progress Papers", pages = "2", pages = "65--66", keywords = "variable rate shading, temporal antialiasing", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/stappen_SteFAS/", } @article{unterguggenberger-2021-msh, title = "Conservative Meshlet Bounds for Robust Culling of Skinned Meshes", author = "Johannes Unterguggenberger and Bernhard Kerbl and Jakob Pernsteiner and Michael Wimmer", year = "2021", abstract = "Following recent advances in GPU hardware development and newly introduced rendering pipeline extensions, the segmentation of input geometry into small geometry clusters-so-called meshlets-has emerged as an important practice for efficient rendering of complex 3D models. Meshlets can be processed efficiently using mesh shaders on modern graphics processing units, in order to achieve streamlined geometry processing in just two tightly coupled shader stages that allow for dynamic workload manipulation in-between. The additional granularity layer between entire models and individual triangles enables new opportunities for fine-grained visibility culling methods. However, in contrast to static models, view frustum and backface culling on a per-meshlet basis for skinned, animated models are difficult to achieve while respecting the conservative spatio-temporal bounds that are required for robust rendering results. In this paper, we describe a solution for computing and exploiting relevant conservative bounds for culling meshlets of models that are animated using linear blend skinning. By enabling visibility culling for animated meshlets, our approach can help to improve rendering performance and alleviate bottlenecks in the notoriously performanceand memory-intensive skeletal animation pipelines of modern real-time graphics applications.", month = oct, journal = "Computer Graphics Forum", volume = "40", number = "7", issn = "1467-8659", doi = "10.1111/cgf.14401", booktitle = "Computer Graphics Forum", pages = "13", publisher = "Eurographics Association", pages = "57--69", keywords = "real-time rendering, meshlet, mesh shader, task shader, view frustum culling, backface culling, Vulkan, vertex skinning, animation, conservative bounds, bounding boxes, Rodrigues' rotation formula, spatio-temporal bounds", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/unterguggenberger-2021-msh/", } @talk{kerbl_2021_hdg, title = "Providing Highly Detailed Geometry for Cloud and Edge Real-Time Rendering", author = "Bernhard Kerbl", year = "2021", abstract = "Mesh shading was recently introduced as a topical GPU feature in the NVIDIA Turing and AMD RDNA2 GPU architectures, offering an alternative pathway for executing the transformation, generation and augmentation of geometry for hardware rasterization. Future trends in game development will rely on mesh shading and “meshlets”, using highly detailed meshes with deep level of detail hierarchies. Particularly powerful applications of meshlets include arbtirary culling and subdivision methods. Furthermore, advanced pre-computation include visibility and lighting information that can be stored on a per-meshlet basis, thus promoting the compression of attributes through quantization and the acceleration of computations via hierarchical processing. Although meshlets can be comprised from arbitrary assemblages of primitives, their benefits are highest when meshlet formation is done in a way that already takes the usecase into account. Individual formation procedures can be defined in order to achieve specific goals. As an example, we may generate meshlets that are optimized for global illumination techniques, by minimizing their curvature and variance in material coefficients. Incoming light can then be ray-traced and cached per meshlet, along with view-dependent variance encoded in a discretized data structure. More uniform meshlets thus require less data transferred for accurately approximating their global illumination, reducing the consumption of critical memory bandwidth. We may also partition entire scenes into meshlets that foster fast visibility culling for large groups of primitives, without transforming even a single vertex. In fact, meshlet formation policies can leverage arbitrary attributes, such as the distribution of UV coordinates, ambient occlusion or mesh topology in order to optimize them according to desired runtime criteria. Cloud gaming offers a unique opportunity for leveraging this technology at a larger scale: dedicated data storages and servers can maintain multiple copies of complex triangle meshes, each partitioned by a particular meshlet formation policy. A live monitor can react to a specific bottleneck by dynamically switching meshlets to best accommodate the current GPU resource requirements. In this talk, we will present the various possibilities for real-time rendering to benefit from mesh shading by means of optimized meshlet formation procedures.", month = jul, event = "InnovWave 2021", location = "online", keywords = "cloud, real-time, rendering", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/kerbl_2021_hdg/", } @article{SCHUETZ-2021-PCC, title = "Rendering Point Clouds with Compute Shaders and Vertex Order Optimization", author = "Markus Sch\"{u}tz and Bernhard Kerbl and Michael Wimmer", year = "2021", 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. We 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. ", month = jul, journal = "Computer Graphics Forum", volume = "40", number = "4", issn = "1467-8659", doi = "10.1111/cgf.14345", booktitle = "techreport", pages = "12", publisher = "Eurographics Association", pages = "115--126", keywords = "point-based rendering, compute shader, real-time rendering", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/SCHUETZ-2021-PCC/", } @inproceedings{kenzel_michael_2021_cuda, title = "CUDA and Applications to Task-based Programming", author = "Michael Kenzel and Bernhard Kerbl and Martin Winter and Markus Steinberger", year = "2021", abstract = "To provide a profound understanding of how CUDA applications can achieve peak performance, the first two parts of this tutorial outline the modern CUDA architecture. Following a basic introduction, we expose how language features are linked to---and constrained by---the underlying physical hardware components. Furthermore, we describe common applications for massively parallel programming, offer a detailed breakdown of potential issues, and list ways to mitigate performance impacts. An exemplary analysis of PTX and SASS snippets illustrates how code patterns in CUDA are mapped to actual hardware instructions. In parts 3 and 4, we focus on novel features that were enabled by the arrival of CUDA 10+ toolkits and the Volta+ architectures, such as ITS, tensor cores, and the graph API. In addition to basic use case demonstrations, we outline our own experiences with these capabilities and their potential performance benefits. We also discuss how long-standing best practices are affected by these changes and describe common caveats for dealing with legacy code on recent GPU models. We show how these considerations can be implemented in practice by presenting state-of-the-art research into task-based GPU scheduling, and how the dynamic adjustment of thread roles and group configurations can significantly increase performance.", month = may, booktitle = "Eurographics 2021 - Tutorials", doi = "10.2312/egt.20211037", editor = "Carol O'Sullivan and Dieter Schmalstieg", location = "Vienna", publisher = "The Eurographics Association", pages = "5", pages = "1--5", keywords = "Parallel Programming, GPU", URL = "https://www.cg.tuwien.ac.at/research/publications/2021/kenzel_michael_2021_cuda/", } @misc{kerbl-2020-improvencoding, title = "Improved Triangle Encoding for Cached Adaptive Tessellation", author = "Linus Horvath and Bernhard Kerbl and Michael Wimmer", year = "2020", month = jul, location = "online", event = "HPG 2020", Conference date = "Poster presented at HPG 2020 (2020-05-01--2020-06-22)", keywords = "GPU, tessellation, real-time", URL = "https://www.cg.tuwien.ac.at/research/publications/2020/kerbl-2020-improvencoding/", } @inproceedings{tatzgern-2020-sst, title = "Stochastic Substitute Trees for Real-Time Global Illumination", author = "Wolfgang Tatzgern and Benedikt Mayr and Bernhard Kerbl and Markus Steinberger", year = "2020", abstract = "With the introduction of hardware-supported ray tracing and deep learning for denoising, computer graphics has made a considerable step toward real-time global illumination. In this work, we present an alternative global illumination method: The stochastic substitute tree (SST), a hierarchical structure inspired by lightcuts with light probability distributions as inner nodes. Our approach distributes virtual point lights (VPLs) in every frame and efficiently constructs the SST over those lights by clustering according to Morton codes. Global illumination is approximated by sampling the SST and considers the BRDF at the hit location as well as the SST nodes’ intensities for importance sampling directly from inner nodes of the tree. To remove the introduced Monte Carlo noise, we use a recurrent autoencoder. In combination with temporal filtering, we deliver real-time global illumination for complex scenes with challenging light distributions.", month = may, event = "I3D ’20", booktitle = "Symposium on Interactive 3D Graphics and Games", pages = "1--9", URL = "https://www.cg.tuwien.ac.at/research/publications/2020/tatzgern-2020-sst/", } @inproceedings{unterguggenberger-2020-fmvr, title = "Fast Multi-View Rendering for Real-Time Applications", author = "Johannes Unterguggenberger and Bernhard Kerbl and Markus Steinberger and Dieter Schmalstieg and Michael Wimmer", year = "2020", abstract = "Efficient rendering of multiple views can be a critical performance factor for real-time rendering applications. Generating more than one view multiplies the amount of rendered geometry, which can cause a huge performance impact. Minimizing that impact has been a target of previous research and GPU manufacturers, who have started to equip devices with dedicated acceleration units. However, vendor-specific acceleration is not the only option to increase multi-view rendering (MVR) performance. Available graphics API features, shader stages and optimizations can be exploited for improved MVR performance, while generally offering more versatile pipeline configurations, including the preservation of custom tessellation and geometry shaders. In this paper, we present an exhaustive evaluation of MVR pipelines available on modern GPUs. We provide a detailed analysis of previous techniques, hardware-accelerated MVR and propose a novel method, leading to the creation of an MVR catalogue. Our analyses cover three distinct applications to help gain clarity on overall MVR performance characteristics. Our interpretation of the observed results provides a guideline for selecting the most appropriate one for various use cases on different GPU architectures.", month = may, isbn = "978-3-03868-107-6", organization = "Eurographics", location = "online", event = "EGPGV 2020", editor = "Frey, Steffen and Huang, Jian and Sadlo, Filip", doi = "10.2312/pgv.20201071", booktitle = "Eurographics Symposium on Parallel Graphics and Visualization", pages = "13--23", keywords = "Real-Time Rendering, Rasterization, Multi-View, OVR_multiview, Geometry Shader, Evaluation", URL = "https://www.cg.tuwien.ac.at/research/publications/2020/unterguggenberger-2020-fmvr/", } @misc{kerbl_2019_planet_poster, title = "Real-time Rendering of Procedural Planets at Arbitrary Altitudes", author = "Florian Michelic and Michael Kenzel and Karl Haubenwallner and Bernhard Kerbl and Markus Steinberger", year = "2019", abstract = "Focusing on real-time, high-fidelity rendering, we present a novel approach for combined consideration of four major phenomena that define the visual representation of entire planets: We present a simple and fast solution for a distortion-free generation of 3D planetary terrain, spherical ocean waves and efficient rendering of volumetric clouds along with atmospheric scattering. Our approach to terrain and ocean mesh generation relies on a projected, persistent grid that can instantaneously and smoothly adapt to fast-changing viewpoints. For generating planetary ocean surfaces, we present a wave function that creates seamless, evenly spaced waves across the entire planet without causing unsightly artifacts. We further show how to render volumetric clouds in combination with precomputed atmospheric scattering and account for their contribution to light transport above ground. Our method provides mathematically consistent approximations of cloud-atmosphere interactions and works for any view point and direction, ensuring continuous transitions in appearance as the viewer moves from ground to space. Among others, our approach supports cloud shadows, light shafts, ocean reflections, and earth shadows on the clouds. The sum of these effects can be visualized at more than 120 frames per second on current graphics processing units.", month = may, note = "Voted best poster of I3D '19", location = "Montreal, Canada", event = "I3D 2019", Conference date = "Poster presented at I3D 2019 (2019-05-21--2019-05-23)", keywords = "planet, rendering", URL = "https://www.cg.tuwien.ac.at/research/publications/2019/kerbl_2019_planet_poster/", }