Research map / 3D vision / Gaussian splatting
Geometric Probing for Isotropic Optimization Manifold in Sparse-View 3D Gaussian Splatting
Yunlong Zhao, Xiaoheng Deng, Hongyan Xu, Yichao Cao, Keke Huang, Shuo Yang, Xiangjian He, Lei Fan, Zhuohua Qiu, Xiu Su
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 Attribute-Space Probing (ablation) | 3DGS · LLFF (3-view) | PSNR: 16.46 -> 19.38 | Improved |
| add Viewpoint-Space Probing (ablation) | 3DGS · LLFF (3-view) | PSNR: 16.46 -> 18.75 | Improved |
| add VSP on top of ASP (ablation) | StableGS · LLFF (3-view) | PSNR: 19.38 -> 21.19 | Improved |
| add position probing to 3DGS (ablation) | 3DGS · LLFF (3-view) | PSNR: 16.46 -> 18.92 | Improved |
| add opacity probing to 3DGS (ablation) | 3DGS · LLFF (3-view) | PSNR: 16.46 -> 17.85 | Improved |
| add rotation/scale probing to 3DGS (ablation) | 3DGS · LLFF (3-view) | PSNR: 16.46 -> 17.52 | Improved |
| combine all three ASP axes vs sum of single axes (ablation) | ASP · LLFF (3-view) | PSNR: +4.91 dB -> +2.92 dB | Mixed |
| add interpolation probe to occlusion probe in VSP (ablation) | VSP · LLFF (3-view) | PSNR: 19.87 -> 20.31 | Improved |
| add parallax translation to occlusion + interpolation probes (ablation) | VSP · LLFF (3-view) | PSNR: 20.31 -> 21.19 | Improved |
| use all three probing modes versus pairs (ablation) | VSP · LLFF (3-view) | PSNR: 20.09-20.31 -> 21.19 | Improved |
| perturb loss weight lambda_ASP by 0.1 (ablation) | StableGS · LLFF (3-view) | PSNR: 21.19 -> 21.06 | No clear effect |
| perturb probe magnitude c_phi by 0.01 (ablation) | StableGS · LLFF (3-view) | PSNR: 21.19 -> 21.14 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- DropGaussian — DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025) · better on 5 of 5 shared results
- DNGaussian — DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization (CVPR 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
- CoR-GS — CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization (ECCV 2024) · 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
- TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization (ICML 2026 · similarity 0.91)
- Path Matters: Unveiling Geometric Implicit Bias via Curvature-Aware Sparse View Optimization (ICLR 2026 · similarity 0.91)
- Improving Sparse-View 3DGS Generalization via Flat Minima Optimization (ECCV 2026 · similarity 0.91)
- Gradient-Direction-Aware Density Control for 3D Gaussian Splatting (ICLR 2026 · similarity 0.91)
- DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds (CVPR 2025 · similarity 0.90)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · 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.
