Research map / 3D vision / Gaussian splatting
GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views
Boyao Zhou, Shunyuan Zheng, Hanzhang Tu, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, Yebin Liu
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 |
|---|---|---|---|
| add joint training of depth estimation and Gaussian rendering (ablation) | GPS-Gaussian · Synthetic human-only (depth supervised) | PSNR: 23.97 -> 25.05 | Improved |
| add joint training of depth estimation and Gaussian rendering (ablation) | GPS-Gaussian · Synthetic human-only | EPE: 1.587 -> 1.494 | Improved |
| add depth encoder before Gaussian parameter decoding (ablation) | GPS-Gaussian · Synthetic human-only | LPIPS: 0.204 -> 0.121 | Improved |
| add depth encoder (ablation) | GPS-Gaussian · Synthetic human-only | PSNR: 23.84 -> 25.05 | Improved |
| add geometry regularization (ablation) | GPS-Gaussian+ · Captured human-scene data | PSNR: 32.04 -> 33.74 | Improved |
| add epipolar attention (ablation) | GPS-Gaussian+ · Captured human-scene data | PSNR: 32.00 -> 33.74 | Improved |
| add depth residual map (ablation) | GPS-Gaussian+ · Captured human-scene data | PSNR: 33.31 -> 33.74 | Improved |
| use GPS-Gaussian+ instead of GPS-Gaussian (no depth supervision) (ablation) | GPS-Gaussian · Synthetic human-only | EPE: 4.066 -> 3.133 | Improved |
| use GPS-Gaussian+ instead of GPS-Gaussian (ablation) | GPS-Gaussian · Captured human-scene data | PSNR: 31.84 -> 33.74 | Improved |
| add depth supervision (ablation) | GPS-Gaussian · Synthetic human-only | EPE: 4.066 -> 1.494 | Improved |
| infer with 6 cameras instead of 8 cameras | GPS-Gaussian · THuman2.0 | PSNR: 25.57 -> 23.03 | Hurt |
| use GPS-Gaussian instead of ENeRF under 6-camera inference | GPS-Gaussian · THuman2.0 camera sparsity | PSNR: 21.78 -> 23.03 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 2024) · better on 4 of 4 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
- GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis (CVPR 2024 · similarity 0.97)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.92)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.92)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (CVPR 2024 · similarity 0.91)
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.
