Research map / 3D vision / Gaussian splatting
Path Matters: Unveiling Geometric Implicit Bias via Curvature-Aware Sparse View Optimization
Canran Xiao, Liaoyuan Fan, Yanbin Li, Jing Tang, Peilai Yu
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 optimal camera trajectory generation (ablation) | Sparse-view 3DGS · DTU (ratio 0.2) | PSNR: 24.20 -> 27.05 | Improved |
| add synthetic camera view construction (ablation) | Sparse-view 3DGS · DTU (ratio 0.2) | PSNR: 24.38 -> 27.05 | Improved |
| add trajectory smoothness constraint (ablation) | Sparse-view 3DGS · DTU (ratio 0.4) | PSNR: 26.84 -> 27.89 | Improved |
| add occlusion handling (ablation) | Sparse-view 3DGS · DTU (ratio 0.2) | PSNR: 24.58 -> 27.05 | Improved |
| raise curvature coverage from 54.8% to 88.9% (ablation) | 3DGS trajectory · Mip-NeRF 360 (4 scenes, 12 views) | PSNR: +3.9 dB | Improved |
| raise curvature coverage from low to high (ablation) | 3DGS trajectory · LLFF Fern | PSNR: 20.4 -> 22.0 | Improved |
| use smooth trajectory instead of jittery at similar coverage (ablation) | 3DGS trajectory · Mip-NeRF 360 Garden | PSNR: 24.5 -> 26.1 | Improved |
| use smooth trajectory (green) instead of sharp-twist trajectory (red) (ablation) | 3DGS on LEGO excavator · Blender LEGO (9 views) | PSNR: 20.15 -> 24.22 | Improved |
| use curvature weights (alpha 0.3, beta 0.7) instead of (1.0, 0.0) (ablation) | Trajectory optimization · DTU (ratio 0.2) | PSNR: 26.07 -> 27.05 | Improved |
| refine depth with uncertainty-weighted fusion (ablation) | Synthetic views · Blender Lego (6 views) | PSNR: 26.8 -> 27.3 | Improved |
| filter synthetic views with visibility and consistency (ablation) | Synthetic views · Blender Lego (6 views) | PSNR: 26.2 -> 27.3 | Improved |
| add 5% relative depth noise (ablation) | Synthetic view construction · Blender Lego (6 views) | PSNR: 27.3 -> 26.9 | Hurt |
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.
- NexusGS — NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting (CVPR 2025) · better on 5 of 5 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
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.91)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.91)
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.91)
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.
