Michael Steiner
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Michael Steiner has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Lukas Radl
Graz University of Technology, Graz, Austria
7 shared publications - Markus Steinberger
Graz University of Technology
7 shared publications - Thomas Köhler
Graz University of Technology, Graz, Austria
4 shared publications - Felix Windisch
Graz University of Technology
3 shared publications - Bernhard Kerbl
TU Wien Austria
2 shared publications - Dieter Schmalstieg
VISUS, University of Stuttgart, Stuttgart, Germany
2 shared publications
Latest Publications
- 12 September 2026
- Published by Springer Nature
- p. 307-325
Confidence-Based Mesh Extraction from 3D Gaussians
- 12 September 2026
- Published by Springer Nature
- p. 307-325
Confidence-Based Mesh Extraction from 3D Gaussians
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessA LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessSOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction
- Open Access
- 19 September 2025
- Published by Wiley in Computer Graphics Forum
Image‐Based Spatio‐Temporal Interpolation for Split Rendering
Low‐powered devices – such as small form factor head‐mounted displays (HMDs) – struggle to deliver a smooth and high‐quality viewing experience, due to their limited power and rendering capabilities. Cloud rendering attempts to solve the quality issue, but leads to prohibitive latency and bandwidth requirements, hindering use with HMDs over mobile connections or even over Wifi. One solution – split rendering – where frames are partially rendered on the client device, often either requires geometry and rendering hardware, or struggles to generate frames faithfully under viewpoint changes and object motion. Our method enables spatio‐temporal interpolation via bidirectional reprojection to efficiently generate intermediate frames in a split rendering setting, while limiting the communication cost and relying purely on image‐based rendering. Furthermore, our method is robust to modest connectivity issues and handles effects such as dynamic smooth shadows.
- 19 September 2025
- Published by Wiley in Computer Graphics Forum
Open AccessImage‐Based Spatio‐Temporal Interpolation for Split Rendering
Low‐powered devices – such as small form factor head‐mounted displays (HMDs) – struggle to deliver a smooth and high‐quality viewing experience, due to their limited power and rendering capabilities. Cloud rendering attempts to solve the quality issue, but leads to prohibitive latency and bandwidth requirements, hindering use with HMDs over mobile connections or even over Wifi. One solution – split rendering – where frames are partially rendered on the client device, often either requires geometry and rendering hardware, or struggles to generate frames faithfully under viewpoint changes and object motion. Our method enables spatio‐temporal interpolation via bidirectional reprojection to efficiently generate intermediate frames in a split rendering setting, while limiting the communication cost and relying purely on image‐based rendering. Furthermore, our method is robust to modest connectivity issues and handles effects such as dynamic smooth shadows.
- Top Cited PapersOpen Access
- 22 May 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 8 (1) , 1-22
VRSplat: Fast and Robust Gaussian Splatting for Virtual Reality
3D Gaussian Splatting (3DGS) has rapidly become a leading technique for novel-view synthesis, providing exceptional performance through efficient software-based GPU rasterization. Its versatility enables real-time applications, including on mobile and lower-powered devices. However, 3DGS faces key challenges in virtual reality (VR): (1) temporal artifacts, such as popping during head movements, (2) projection-based distortions that result in disturbing and view-inconsistent floaters, and (3) reduced framerates when rendering large numbers of Gaussians, falling below the critical threshold for VR. Compared to desktop environments, these issues are drastically amplified by large field-of-view, constant head movements, and high resolution of head-mounted displays (HMDs). In this work, we introduce VRSplat: we combine and extend several recent advancements in 3DGS to address challenges of VR holistically. We show how the ideas of Mini-Splatting, StopThePop, and Optimal Projection can complement each other, by modifying the individual techniques and core 3DGS rasterizer. Additionally, we propose an efficient foveated rasterizer that handles focus and peripheral areas in a single GPU launch, avoiding redundant computations and improving GPU utilization. Our method also incorporates a fine-tuning step that optimizes Gaussian parameters based on StopThePop depth evaluations and Optimal Projection. We validate our method through a controlled user study with 25 participants, showing a strong preference for VRSplat over other configurations of Mini-Splatting. VRSplat is the first, systematically evaluated 3DGS approach capable of supporting modern VR applications, achieving 72+ FPS while eliminating popping and stereo-disrupting floaters.
- 22 May 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 8 (1) , 1-22
Top Cited PapersOpen AccessVRSplat: Fast and Robust Gaussian Splatting for Virtual Reality
3D Gaussian Splatting (3DGS) has rapidly become a leading technique for novel-view synthesis, providing exceptional performance through efficient software-based GPU rasterization. Its versatility enables real-time applications, including on mobile and lower-powered devices. However, 3DGS faces key challenges in virtual reality (VR): (1) temporal artifacts, such as popping during head movements, (2) projection-based distortions that result in disturbing and view-inconsistent floaters, and (3) reduced framerates when rendering large numbers of Gaussians, falling below the critical threshold for VR. Compared to desktop environments, these issues are drastically amplified by large field-of-view, constant head movements, and high resolution of head-mounted displays (HMDs). In this work, we introduce VRSplat: we combine and extend several recent advancements in 3DGS to address challenges of VR holistically. We show how the ideas of Mini-Splatting, StopThePop, and Optimal Projection can complement each other, by modifying the individual techniques and core 3DGS rasterizer. Additionally, we propose an efficient foveated rasterizer that handles focus and peripheral areas in a single GPU launch, avoiding redundant computations and improving GPU utilization. Our method also incorporates a fine-tuning step that optimizes Gaussian parameters based on StopThePop depth evaluations and Optimal Projection. We validate our method through a controlled user study with 25 participants, showing a strong preference for VRSplat over other configurations of Mini-Splatting. VRSplat is the first, systematically evaluated 3DGS approach capable of supporting modern VR applications, achieving 72+ FPS while eliminating popping and stereo-disrupting floaters.
- Open Access
- 9 August 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 7 (3) , 1-22
Frustum Volume Caching for Accelerated NeRF Rendering
Neural Radiance Fields (NeRFs) have revolutionized the field of inverse rendering due to their ability to synthesize high-quality novel views and applicability in practical contexts. NeRFs leverage volume rendering, evaluating view-dependent color at each sample with an expensive network, where a high computational burden is placed on extracting an informative, view-independent latent code. We propose a temporal coherence method to accelerate NeRF rendering by caching the latent codes of all samples in an initial viewpoint and reusing them in consecutive frames. By utilizing a sparse frustum volume grid for caching and performing lookups via backward reprojection, we enable temporal reuse of NeRF samples while maintaining the ability to re-evaluate view-dependent effects efficiently. To facilitate high-fidelity rendering from our cache with interactive framerates, we propose a novel cone encoding and explore a training scheme to induce local linearity into the latent information. Extensive experimental evaluation demonstrates that these choices enable high-quality real-time rendering from our cache, even when reducing latent code size significantly. Our proposed method scales exceptionally well for large networks, and our highly optimized real-time implementation allows for cache initialization at runtime. For offline rendering of high-quality video sequences with expensive supersampled effects like motion blur or depth of field, our approach provides speed-ups of up to 2×.
- 9 August 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 7 (3) , 1-22
Open AccessFrustum Volume Caching for Accelerated NeRF Rendering
Neural Radiance Fields (NeRFs) have revolutionized the field of inverse rendering due to their ability to synthesize high-quality novel views and applicability in practical contexts. NeRFs leverage volume rendering, evaluating view-dependent color at each sample with an expensive network, where a high computational burden is placed on extracting an informative, view-independent latent code. We propose a temporal coherence method to accelerate NeRF rendering by caching the latent codes of all samples in an initial viewpoint and reusing them in consecutive frames. By utilizing a sparse frustum volume grid for caching and performing lookups via backward reprojection, we enable temporal reuse of NeRF samples while maintaining the ability to re-evaluate view-dependent effects efficiently. To facilitate high-fidelity rendering from our cache with interactive framerates, we propose a novel cone encoding and explore a training scheme to induce local linearity into the latent information. Extensive experimental evaluation demonstrates that these choices enable high-quality real-time rendering from our cache, even when reducing latent code size significantly. Our proposed method scales exceptionally well for large networks, and our highly optimized real-time implementation allows for cache initialization at runtime. For offline rendering of high-quality video sequences with expensive supersampled effects like motion blur or depth of field, our approach provides speed-ups of up to 2×.
- Top Cited PapersOpen Access
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-17
StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering
Gaussian Splatting has emerged as a prominent model for constructing 3D representations from images across diverse domains. However, the efficiency of the 3D Gaussian Splatting rendering pipeline relies on several simplifications. Notably, reducing Gaussian to 2D splats with a single viewspace depth introduces popping and blending artifacts during view rotation. Addressing this issue requires accurate per-pixel depth computation, yet a full per-pixel sort proves excessively costly compared to a global sort operation. In this paper, we present a novel hierarchical rasterization approach that systematically resorts and culls splats with minimal processing overhead. Our software rasterizer effectively eliminates popping artifacts and view inconsistencies, as demonstrated through both quantitative and qualitative measurements. Simultaneously, our method mitigates the potential for cheating view-dependent effects with popping, ensuring a more authentic representation. Despite the elimination of cheating, our approach achieves comparable quantitative results for test images, while increasing the consistency for novel view synthesis in motion. Due to its design, our hierarchical approach is only 4% slower on average than the original Gaussian Splatting. Notably, enforcing consistency enables a reduction in the number of Gaussians by approximately half with nearly identical quality and view-consistency. Consequently, rendering performance is nearly doubled, making our approach 1.6x faster than the original Gaussian Splatting, with a 50% reduction in memory requirements. Our renderer is publicly available at https://github.com/r4dl/StopThePop.
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-17
Top Cited PapersOpen AccessStopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering
Gaussian Splatting has emerged as a prominent model for constructing 3D representations from images across diverse domains. However, the efficiency of the 3D Gaussian Splatting rendering pipeline relies on several simplifications. Notably, reducing Gaussian to 2D splats with a single viewspace depth introduces popping and blending artifacts during view rotation. Addressing this issue requires accurate per-pixel depth computation, yet a full per-pixel sort proves excessively costly compared to a global sort operation. In this paper, we present a novel hierarchical rasterization approach that systematically resorts and culls splats with minimal processing overhead. Our software rasterizer effectively eliminates popping artifacts and view inconsistencies, as demonstrated through both quantitative and qualitative measurements. Simultaneously, our method mitigates the potential for cheating view-dependent effects with popping, ensuring a more authentic representation. Despite the elimination of cheating, our approach achieves comparable quantitative results for test images, while increasing the consistency for novel view synthesis in motion. Due to its design, our hierarchical approach is only 4% slower on average than the original Gaussian Splatting. Notably, enforcing consistency enables a reduction in the number of Gaussians by approximately half with nearly identical quality and view-consistency. Consequently, rendering performance is nearly doubled, making our approach 1.6x faster than the original Gaussian Splatting, with a 50% reduction in memory requirements. Our renderer is publicly available at https://github.com/r4dl/StopThePop.
- 1 May 2018
- Published by Wiley in Journal of Turbomachinery
- Vol. 140 (6)
Aerodynamic Performance of Turbine Center Frames With Purge Flows—Part I: The Influence of Turbine Purge Flow Rates
This two-part paper deals with the influence of high-pressure turbine (HPT) purge flows on the aerodynamic performance of turbine center frames (TCF). Measurements were carried out in a product-representative one and a half-stage turbine test setup. Four individual purge mass flows differing in flow rate, pressure, and temperature were injected through the hub and tip, forward and aft cavities of the unshrouded HPT rotor. Two TCF designs, equipped with nonturning struts, were tested and compared. In this first part of the paper, the influence of different purge flow rates (PFR) is discussed, while in the second part of the paper, the impact of the individual hub and tip purge flows on the TCF aerodynamics is investigated. The acquired measurement data illustrate that the interaction of the ejected purge flow with the main flow enhances the secondary flow structures through the TCF duct. Depending on the PFR, the radial migration of purge air onto the strut surfaces directly impacts the loss behavior of the duct. The losses associated with the flow close to the struts and in the strut wakes are highly dependent on the relative position between the HPT vane and the strut leading edge (LE), as well as the interaction between vane wake and ejected purge flow. This first-time experimental assessment demonstrates that a reduction in the purge air requirement benefits the engine system performance by lowering the TCF total pressure loss.
- 1 May 2018
- Published by Wiley in Journal of Turbomachinery
- Vol. 140 (6)
Aerodynamic Performance of Turbine Center Frames With Purge Flows—Part I: The Influence of Turbine Purge Flow Rates
This two-part paper deals with the influence of high-pressure turbine (HPT) purge flows on the aerodynamic performance of turbine center frames (TCF). Measurements were carried out in a product-representative one and a half-stage turbine test setup. Four individual purge mass flows differing in flow rate, pressure, and temperature were injected through the hub and tip, forward and aft cavities of the unshrouded HPT rotor. Two TCF designs, equipped with nonturning struts, were tested and compared. In this first part of the paper, the influence of different purge flow rates (PFR) is discussed, while in the second part of the paper, the impact of the individual hub and tip purge flows on the TCF aerodynamics is investigated. The acquired measurement data illustrate that the interaction of the ejected purge flow with the main flow enhances the secondary flow structures through the TCF duct. Depending on the PFR, the radial migration of purge air onto the strut surfaces directly impacts the loss behavior of the duct. The losses associated with the flow close to the struts and in the strut wakes are highly dependent on the relative position between the HPT vane and the strut leading edge (LE), as well as the interaction between vane wake and ejected purge flow. This first-time experimental assessment demonstrates that a reduction in the purge air requirement benefits the engine system performance by lowering the TCF total pressure loss.