Research map / 3D vision / Gaussian splatting
GSRecon: Efficient Generalizable Gaussian Splatting for Surface Reconstruction from Sparse Views
Hang Yang, Le Hui, Jianjun Qian, Jin Xie, Jian Yang
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 voxel branch for cross-view aggregation to the baseline (ablation) | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.68 -> 1.41 | Improved |
| use point branch instead of voxel branch (ablation) | GSRecon · DTU favorable vs unfavorable sets | mean Chamfer distance: favorable 1.05 -> 1.01; unfavorable 1.41 -> 1.64 | Mixed |
| combine point and voxel branches (ablation) | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.41 -> 1.39 | Improved |
| add geometry-aware cross-view enhancement (GCE) to baseline (ablation) | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.68 -> 1.42 | Improved |
| add GCE after stage 1 to hybrid aggregation model (ablation) | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.39 -> 1.32 | Improved |
| add GCE after stage 2 only to hybrid aggregation model (ablation) | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.39 -> 1.38 | No clear effect |
| add GCE after both stages 1 and 2 (ablation) | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.32 -> 1.30 | Improved |
| use Gaussian rasterization-based generalizable reconstruction instead of volume-rendering implicit methods | GSRecon · DTU unfavorable views | reconstruction time (s): 102 -> 0.8 | Improved |
| use GSRecon instead of UFORecon | GSRecon · DTU unfavorable views | GPU memory (MB): 7102 -> 8410 | Hurt |
| use GSRecon instead of UFORecon | GSRecon · DTU unfavorable set | mean Chamfer distance: 1.56 -> 1.30 | Improved |
| use GSRecon instead of UFORecon on favorable views | GSRecon · DTU favorable set | mean Chamfer distance: 0.99 -> 0.95 | Improved |
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.
- UFORecon — UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024) · better on 6 of 7 shared results
- ReTR — ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction (NeurIPS 2023) · better on 2 of 2 shared results
- VolRecon — VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction (CVPR 2023) · 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
- GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024 · similarity 0.91)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.91)
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.90)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.90)
- FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025 · similarity 0.90)
- GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction (CVPR 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.
