Research map / 3D vision / Gaussian splatting
Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting
Shuangkang Fang, I-Chao Shen, Xuanyang Zhang, Zesheng Wang, Yufeng Wang, Wenrui Ding, Gang YU, Takeo Igarashi
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 anchor-based dropout (ablation) | 3DGS (sparse view) · LLFF (3 views) | PSNR: 19.17 -> 20.47 | Improved |
| add SH dropout on top of anchor dropout (ablation) | DropAnSH-GS · LLFF (3 views) | PSNR: 20.47 -> 20.68 | Improved |
| add SH dropout alone (ablation) | 3DGS (sparse view) · LLFF (3 views) | SSIM: 0.646 -> 0.641 | No clear effect |
| drop SH by degree instead of randomly (ablation) | DropAnSH-GS · Blender (8 views) | PSNR: 25.12 -> 25.50 | Improved |
| replace independent Gaussian dropout with anchor dropout plus SH dropout | DropGaussian · LLFF (3 views) | PSNR: 20.33 -> 20.68 | Improved |
| truncate to SH0 at inference (ablation) | DropAnSH-GS · MipNeRF-360 (12 views) | PSNR: 18.58 (3DGS) -> 19.71; size 143.4 -> 33.8 MB | Improved |
| truncate SH3 to SH2 at inference (ablation) | DropAnSH-GS · MipNeRF-360 (12 views) | PSNR: 19.93 -> 19.95; size 122.6 -> 81.1 MB | Mixed |
| plug DropAnSH-GS into Scaffold-GS | Scaffold-GS · LLFF (3 views) | PSNR: 18.62 -> 19.84 | Improved |
| plug DropAnSH-GS into CoR-GS | CoR-GS · LLFF (3 views) | LPIPS: 0.202 -> 0.203 | No clear effect |
| raise anchor sampling rate from 0.02 to 0.04 (ablation) | DropAnSH-GS · LLFF (3 views) | PSNR: 20.68 -> 19.97 | Hurt |
| use 1 neighbor instead of 10 (ablation) | DropAnSH-GS · LLFF (3 views) | PSNR: 20.68 -> 20.12 | Hurt |
| add anchor and SH dropout to 3DGS: training time | 3DGS · LLFF (3 views) | Training time: 741.6s -> 760.2s | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DropGaussian — DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025) · better on 6 of 6 shared results
- CoR-GS — CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization (ECCV 2024) · better on 2 of 2 shared results
- DropoutGS — DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering (CVPR 2025) · better on 1 of 1 shared result
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
- DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering (CVPR 2025 · similarity 0.93)
- DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025 · similarity 0.93)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.89)
- Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting (NeurIPS 2024 · 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.
