Research map / Point clouds / Shape and surface completion
Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
Jan Bednarik, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua, Noam Aigerman
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 |
|---|---|---|---|
| sample training pairs from a time window of neighbors instead of random pairs (ablation) | OUR · AMA crane | m_sL2: 96.82 -> 66.63 | Improved |
| sample training pairs from a time window of neighbors instead of random pairs (ablation) | OUR · AMA crane | mPCK AUC: 77.08 -> 80.24 | Improved |
| sample training pairs from a time window of neighbors instead of random pairs (ablation) | OUR · AMA crane | Chamfer distance: 0.30 -> 0.31 | Hurt |
| add metric consistency loss (weight 0.1 vs 1e-3) (ablation) | OUR · AMA crane | m_sL2: 232.5 -> 66.6 | Improved |
| add metric consistency loss (weight 1e-2 vs 1e-4) (ablation) | OUR · ANIM cat | m_sL2: 13.2 -> 9.8 | Improved |
| raise metric weight from 0.1 to 1e3 (ablation) | OUR · DFAUST jacks | m_sL2: 28.0 -> 194.2 | Hurt |
| replace AtlasNet with metric-consistent atlas (add metric loss) | AtlasNet · ANIM | m_sL2: 18.40 -> 11.93 | Improved |
| replace AtlasNet with metric-consistent atlas (add metric loss) | AtlasNet · AMA | m_sL2: 86.80 -> 57.12 | Improved |
| replace AtlasNet with metric-consistent atlas (add metric loss) | AtlasNet · AMA | Chamfer distance: 0.30 -> 0.32 | Hurt |
| replace AtlasNet with metric-consistent atlas (add metric loss) | AtlasNet · DFAUST | m_sL2: 31.74 -> 19.81 | Improved |
| train CC with random triplets instead of knn (ablation) | CC · DFAUST jumping_jacks | m_sL2: 105.57 -> 32.74 | Improved |
| use random nrICP matching instead of propagate_simple (ablation) | nrICP · AMA crane | m_sL2: 211.11 -> 172.55 | Improved |
Closest papers by meaning
- Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases (TPAMI 2025 · similarity 0.97)
- Surface Reconstruction From Point Clouds: A Survey and a Benchmark (TPAMI 2024 · similarity 0.89)
- DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction (ECCV 2024 · similarity 0.88)
- Deep Geometric Prior for Surface Reconstruction (CVPR 2019 · similarity 0.88)
- OffsetOPT: Explicit Surface Reconstruction without Normals (CVPR 2025 · similarity 0.86)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.86)
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.
