Research map / 3D vision / Gaussian splatting
3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction
Takeshi Noda, Yu-Shen Liu, Zhizhong Han
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 self-constrained prior f^t (ablation) | Gaussian splatting surface model · DTU | Chamfer distance: 0.56 -> 0.50 | Improved |
| add opacity constraint L_SCP (ablation) | Gaussian splatting surface model · DTU | Chamfer distance: 0.53 -> 0.50 | Improved |
| update prior from f^0 to f^1 and f^2 (ablation) | Gaussian splatting surface model · DTU | Chamfer distance: 0.54 -> 0.52 -> 0.50 | Improved |
| add Gaussian outlier removal (ablation) | Gaussian splatting surface model · DTU | Chamfer distance: 0.53 -> 0.50 | Improved |
| add Gaussian projection toward surface (ablation) | Gaussian splatting surface model · DTU | Chamfer distance: 0.51 -> 0.50 | Improved |
| shrink bandwidth progressively 1, 0.5, 0.25 (ablation) | Gaussian splatting surface model · DTU | Chamfer distance: 0.54 -> 0.53 -> 0.51 -> 0.50 | Improved |
| self-constrained prior vs PGSR | Gaussian splatting surface model · DTU | Chamfer distance: 0.53 -> 0.50 | Improved |
| self-constrained prior vs PGSR | Gaussian splatting surface model · Tanks and Temples | F1-score: 0.50 -> 0.51 | No clear effect |
| self-constrained prior vs 3DGS on novel view synthesis | Gaussian splatting surface model · Mip-NeRF 360 (outdoor scenes) | PSNR: 24.64 -> 24.81 | No clear effect |
| self-constrained prior vs 2DGS | Gaussian splatting surface model · NeRF-Synthetic | CD_L1 x100: 2.26 -> 1.87 | Improved |
| add prior-based method but longer training time vs 2DGS | Gaussian splatting surface model · DTU | training time: 19.2min -> 42min | Hurt |
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.
- GSDF — GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction (NeurIPS 2024) · better on 1 of 1 shared result
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · 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
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.91)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.91)
- GaussianUDF: Inferring Unsigned Distance Functions through 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)
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.90)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · 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.
