Research map / 3D vision / Gaussian splatting
VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction
Peng Xiang, Liang Han, Hui Zhang, 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 anchor-calibrated depth loss L_depth (ablation) | VGGS (PGSR baseline) · DTU | Chamfer Distance: 1.51 -> 0.96 | Improved |
| add anchor-calibrated depth loss L_depth (ablation) | VGGS (PGSR baseline) · TNT | F-Score: 0.140 -> 0.174 | Improved |
| add relative depth consistency loss L_RDC alone (ablation) | VGGS (PGSR baseline) · DTU | Chamfer Distance: 1.51 -> 1.31 | Improved |
| add L_RDC on top of L_depth (ablation) | VGGS (PGSR baseline) · DTU | Chamfer Distance: 0.96 -> 0.95 | No clear effect |
| add L_RDC on top of L_depth (ablation) | VGGS (PGSR baseline) · TNT | F-Score: 0.174 -> 0.189 | Improved |
| add normal prior loss L_normal (ablation) | VGGS (PGSR baseline) · DTU | Chamfer Distance: 1.51 -> 1.33 | Improved |
| add L_normal to depth and RDC (ablation) | VGGS (PGSR baseline) · DTU | Chamfer Distance: 0.95 -> 0.91 | Improved |
| add L_normal to depth and RDC (ablation) | VGGS (PGSR baseline) · TNT | F-Score: 0.189 -> 0.194 | Improved |
| use COLMAP Gaussian initialization instead of MASt3R-SfM (ablation) | VGGS (PGSR baseline) · DTU | Chamfer Distance: 0.91 -> 0.95 | Hurt |
| use VGGS instead of MAtCha | VGGS (PGSR baseline) · DTU | Chamfer Distance: 1.16 -> 0.91 | Improved |
| use VGGS instead of MAtCha at 5 views | VGGS (PGSR baseline) · TNT 5 views | F-Score: 0.072 -> 0.076 | Improved |
| use VGGS instead of MAtCha for training cost | VGGS (PGSR baseline) · DTU | training time: 8 mins -> 2 mins | Improved |
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.
- FatesGS — FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025) · better on 4 of 4 shared results
- SparseCraft — SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization (ECCV 2024) · better on 2 of 2 shared results
- NeuSurf — NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024) · better on 1 of 1 shared result
- UFORecon — UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 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
- Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors (ECCV 2026 · similarity 0.92)
- FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025 · similarity 0.92)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · 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 0.89)
- DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025 · similarity 0.89)
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.
