Research map / 3D vision / Gaussian splatting
When 3D Gaussian Splatting Recovers Real Surfaces
Songhe Wang, David Miller
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 |
|---|---|---|---|
| raise SH degree from 3 to 24 (ablation) | 3DGS · DTU (real scenes) | nCD: 0.0090 -> 0.0100 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · MobileBrick (real scenes) | nCD: 0.0600 -> 0.0700 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · YCB-Video (real scenes) | nCD: 0.0420 -> 0.0500 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · T-LESS (real scenes) | nCD: 0.0650 -> 0.0750 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · ScanNet (real scenes) | nCD: 0.0110 -> 0.0120 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · ScanNet++ (real scenes) | nCD: 0.0070 -> 0.0080 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · Matterport3D (real scenes) | nCD: 0.0045 -> 0.0050 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · HM3D (real scenes) | nCD: 0.0047 -> 0.0053 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · Real-scene datasets average | nCD: 0.0220 -> 0.0254 | No clear effect |
| raise SH degree from 3 to 24 (ablation) | 3DGS · Real-scene datasets average | PSNR: 29.6 -> 30.2 | Improved |
| increase SH degree on synthetic shapes (ablation) | 3DGS · Synthetic stress-test shapes | nCD: approximately ~89% of shapes increase in nCD as SH degree increases | Hurt |
| increase SH degree on synthetic shapes (ablation) | 3DGS · Synthetic stress-test shapes | PSNR: average PSNR slightly increases | No clear effect |
Closest papers by meaning
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 2025 · similarity 0.89)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.88)
- Volumetrically Consistent 3D Gaussian Rasterization (CVPR 2025 · similarity 0.88)
- Geometry Field Splatting with Gaussian Surfels (CVPR 2025 · similarity 0.88)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.88)
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.
