StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering
Lukas Radl, Michael Steiner, Mathias Parger, Alexander Weinrauch, Bernhard Kerbl, Markus Steinberger
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper49
- FastGS: Training 3D Gaussian Splatting in 100 SecondsShiwei Ren, Tianci Wen, Yongchun Fang, Biao LuCVPR 2026 · 被引用 55 次
- Dynamic 3D Gaussian Fields for Urban AreasTobias Fischer, Jonas Kulhanek, Samuel Rota Bulò, Lorenzo Porzi 等NeurIPS 2024 · 被引用 52 次
- MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated RenderingWeikai Lin, Yu Feng, Yuhao ZhuASPLOS 2025 · 被引用 30 次
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface ReconstructionJiahe Li, Jiawei Zhang, Youmin Zhang, Xiao Bai 等NeurIPS 2025 · 被引用 18 次
- Faster-GS: Analyzing and Improving Gaussian Splatting OptimizationFlorian Hahlbohm, Linus Franke, Martin Eisemann, Marcus A. MagnorCVPR 2026 · 被引用 16 次
它引用的顶会 Paper18
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman 等ICCV 2021 · 被引用 2,700 次
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 等CVPR 2022 · 被引用 1,603 次
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen 等CVPR 2022 · 被引用 1,237 次
相关 Paper
- AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian RenderingMichael Steiner, Thomas Köhler, Lukas Radl, Felix Windisch 等ICCV 2025 · 被引用 5 次
- GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian SplatsSangeek Hyun, Jae-Pil HeoNeurIPS 2024 · 被引用 17 次
- Hardware-Rasterized Ray-Based Gaussian SplattingSamuel Rota Bulò, Nemanja Bartolovic, Lorenzo Porzi, Peter KontschiederCVPR 2025
- SAP: Exact Sorting in Splatting via Screen-Aligned PrimitivesZhanke Wang, Zhiyan Wang, Kaiqiang Xiong, Jiahao Wu 等NeurIPS 2025 · 被引用 1 次
- EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View SynthesisYancheng Zhang, Guangyu Sun, Chen ChenNeurIPS 2025 · 被引用 2 次
