Research map / 3D vision / Gaussian splatting
SparseSurf: Sparse-View 3D Gaussian Splatting for Surface Reconstruction
Meiying Gu, Jiawei Zhang, Jiahe Li, Xiaohan Yu, Haonan Luo, Jin Zheng, Xiao Bai
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 stereo geometry-texture alignment loss (Lstereo) (ablation) | SparseSurf baseline · DTU large-overlap | Chamfer Distance: 1.810 -> 1.217 | Improved |
| add pseudo-view feature consistency (Lpseudo) (ablation) | SparseSurf with Lstereo · DTU large-overlap | Chamfer Distance: 1.217 -> 0.969 | Improved |
| add train-view feature alignment (Ltrain) (ablation) | SparseSurf with Lstereo+Lpseudo · DTU large-overlap | Chamfer Distance: 0.969 -> 0.886 | Improved |
| SparseSurf vs FatesGS (flattened Gaussians + monocular depth priors) | sparse-view surface reconstruction · DTU little-overlap | Chamfer Distance: 1.37 -> 1.05 | Improved |
| SparseSurf vs FatesGS on large-overlap | sparse-view surface reconstruction · DTU large-overlap | Chamfer Distance: 0.92 -> 0.89 | Improved |
| SparseSurf vs NexusGS on novel view synthesis | sparse-view NVS · DTU sparse NVS | PSNR: 20.21 -> 21.31 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 6 of 6 on most shared results.
- FatesGS — FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025) · better on 5 of 5 shared results
- NexusGS — NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting (CVPR 2025) · better on 3 of 3 shared results
- CoR-GS — CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization (ECCV 2024) · better on 3 of 3 shared results
- NeuSurf — NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024) · better on 2 of 2 shared results
- UFORecon — UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024) · better on 2 of 2 shared results
- Sparse2DGS — Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025) · 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
- FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025 · similarity 0.93)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.93)
- SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction (NeurIPS 2025 · similarity 0.92)
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization (CVPR 2025 · similarity 0.92)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.91)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · 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.
