Research map / 3D vision / Gaussian splatting
NeRF Is a Valuable Assistant for 3D Gaussian Splatting
Shuangkang Fang, I-Chao Shen, Takeo Igarashi, Yufeng Wang, ZeSheng Wang, Yi Yang, Wenrui Ding, Shuchang Zhou
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 edge-based initialization (ablation) | NeRF-GS · Tanks&Temples avg | PSNR: 22.61 -> 24.44 | Improved |
| add edge-based initialization (ablation) | NeRF-GS · DeepBlending avg | PSNR: 29.8 -> 30.7 | Improved |
| add feature sharing between NeRF and GS branches (ablation) | NeRF-GS · Tanks&Temples avg | PSNR: 23.93 -> 24.44 | Improved |
| add residual feature vector (ablation) | NeRF-GS · Tanks&Temples avg | PSNR: 24.09 -> 24.44 | Improved |
| add residual position vector (ablation) | NeRF-GS · DeepBlending avg | PSNR: 30.45 -> 30.7 | Improved |
| use GS-Rays instead of random rays for NeRF branch (ablation) | NeRF-GS · DeepBlending avg | PSNR: 30.22 -> 30.7 | Improved |
| add joint opacity loss (ablation) | NeRF-GS · Tanks&Temples avg | PSNR: 24.35 -> 24.44 | Improved |
| add joint RGB loss (ablation) | NeRF-GS · DeepBlending avg | PSNR: 30.59 -> 30.7 | Improved |
| add NeRF branch loss (joint NeRF training) (ablation) | NeRF-GS · Tanks&Temples avg | PSNR: 23.30 -> 24.44 | Improved |
| add volume regularization (ablation) | NeRF-GS · Tanks&Temples avg | PSNR: 24.29 -> 24.44 | Improved |
| add joint optimization after edge initialization instead of directly optimizing 3DGS (ablation) | 3DGS · DeepBlending avg | PSNR: 29.89 -> 30.7 | Improved |
| use edge-based rather than random initialization for direct 3DGS (ablation) | 3DGS · Tanks&Temples avg | PSNR: 23.65 -> 23.99 | 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.
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · 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
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.92)
- Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields (CVPR 2024 · similarity 0.91)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.91)
- 3D-HGS: 3D Half-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)
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS (NeurIPS 2025 · similarity 0.90)
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.
