Research map / 3D vision / Depth and stereo
SurfelMeshing: Online Surfel-Based Mesh Reconstruction
Thomas Schöps, Torsten Sattler, Marc Pollefeys
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 regularization denoising (ablation) | SurfelMeshing · TUM fr1/desk | mean curvature: 1.1 -> 0.6 | Improved |
| add observation boundary blending (ablation) | SurfelMeshing · TUM fr1/desk | mean curvature: 1.0 -> 0.6 | Improved |
| add regularization denoising (ablation) | SurfelMeshing · TUM fr1/desk | boundary vertices: 2.8% -> 2.3% | Improved |
| add boundary blending (ablation) | SurfelMeshing · TUM fr1/desk | boundary vertices: 3.4% -> 2.3% | Improved |
| add both regularization and blending (ablation) | SurfelMeshing · TUM fr1/xyz | mean curvature: 1.3 -> 0.3 | Improved |
| use incremental remeshing instead of meshing from scratch (ablation) | SurfelMeshing · TUM fr1/desk | mean curvature: 0.6 -> 0.6 | No clear effect |
| use incremental remeshing instead of meshing from scratch (ablation) | SurfelMeshing · TUM fr1/desk | self-intersections: 0.2% -> 0.3% | Hurt |
| use incremental remeshing instead of meshing final cloud from scratch (ablation) | SurfelMeshing · TUM fr1/desk | meshing time: about 5.6 seconds from scratch | Improved |
| replace Laplacian smoothing with the proposed regularization (ablation) | SurfelMeshing · qualitative surfel cloud | shrinkage | Improved |
| replace ElasticFusion with SurfelMeshing | surfel fusion · ICL-NUIM kt0 ground truth trajectory | completeness: 38.8 -> 45.6 | Improved |
| replace ElasticFusion with SurfelMeshing | surfel fusion · ICL-NUIM kt0 ground truth trajectory | accuracy: 96.2 -> 93.5 | Hurt |
| replace InfiniTAM with SurfelMeshing | volumetric fusion · ICL-NUIM kt0 ground truth trajectory | accuracy: 76.4 -> 93.5 | Improved |
Later papers that compared with this method
2 later accepted papers report SurfelMeshing as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Gaussian Fusion: Accurate 3D Reconstruction via Geometry-Guided Displacement Interpolation (ICCV 2021 · better on 6 of 10 shared results)
- DeepSurfels: Learning Online Appearance Fusion (CVPR 2021 · 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
- SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction (NeurIPS 2025 · similarity 0.89)
- SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars (ICLR 2025 · similarity 0.87)
- Geometry Field Splatting with Gaussian Surfels (CVPR 2025 · similarity 0.86)
- MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views (CVPR 2025 · similarity 0.85)
- Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels (NeurIPS 2024 · similarity 0.85)
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (NeurIPS 2025 · similarity 0.85)
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.
