Research map / 3D vision / Gaussian splatting
Universal Beta Splatting
Rong Liu, Zhongpai Gao, Benjamin Planche, Meida Chen, Van Nguyen Nguyen, Meng Zheng, Anwesa Choudhuri, Terrence Chen, Yue Wang, Andrew Feng, Ziyan Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use N-D Beta kernels instead of Gaussian kernels | 3DGS · NeRF Synthetic | PSNR: +1.13 dB | Improved |
| use N-D Beta kernels instead of 6DGS | 6DGS · Mip-NeRF 360 | PSNR: +2.31 dB | Improved |
| use Beta kernels instead of 3DGS | 3DGS · 6DGS-PBR | PSNR: +12.70 dB | Improved |
| use UBS-7D instead of 7DGS | 7DGS · D-NeRF | PSNR: +0.51 dB | Improved |
| add spatial-orthogonal Cholesky parameterization (ablation) | UBS · 6DGS/7DGS-PBR ablation scenes | PSNR: 31.60 -> 32.16 | Improved |
| add Cholesky to skew-symmetric rotation parameterization (ablation) | UBS · 6DGS/7DGS-PBR ablation scenes | PSNR: 31.87 -> 32.16 | Improved |
| add Beta-modulated conditioning (ablation) | UBS · 6DGS/7DGS-PBR ablation scenes | PSNR: 31.63 -> 32.16 | Improved |
| add Beta-modulated opacity (ablation) | UBS · 6DGS/7DGS-PBR ablation scenes | PSNR: 28.64 -> 32.16 | Improved |
| add custom CUDA implementation (ablation) | UBS · ablation scenes | train time (min): 30.7 -> 12.9 | Improved |
| reduce primitive cap from 300K to 100K (ablation) | UBS-6D · NeRF Synthetic | PSNR: 34.89 -> 34.42 | Hurt |
| use first-order Taylor instead of matrix exponential for rotation (ablation) | UBS-3D · bicycle | training time: 3h6m -> 1h | Improved |
| use spatial-orthogonal skew-symmetric instead of pure Cholesky (ablation) | UBS-3D · bicycle | PSNR: 25.28 -> 25.54 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- 6DGS — 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering (ICLR 2025) · better on 6 of 6 shared results
- 7DGS — 7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting (ICCV 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.90)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Hardware-Rasterized Ray-Based Gaussian Splatting (CVPR 2025 · similarity 0.89)
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS (NeurIPS 2025 · similarity 0.89)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.89)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
