Research map / 3D vision / Depth and stereo
Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use first-order warp derivatives instead of second-order derivatives | Diff vs. Pa17 · Cylinder, noise varied from 1 to 5 pixels | mean shape error: 9.5−14.7 degrees vs. 9.8−12.3 degrees | Helped |
| Use Diff instead of Pa17 for normal evaluation | NRSfM point reconstruction from 10 images · 10-image point reconstruction | time to evaluate normals: 1.5 seconds vs. 10 ms | Helped |
| Use first-order rather than refined second-order derivatives | Image-pair warp processing · each image pair | derivative computation time: 2-5 seconds vs. 20-30 ms | Helped |
| Add isometric, conformal, or equiareal metric-preserving constraints (ablation) | Diff · Cylinder | reconstruction error | Helped |
| Add isometric, conformal, or equiareal metric-preserving constraints (ablation) | Diff · Tshirt | reconstruction error | No clear effect |
| Add isometric, conformal, or equiareal metric-preserving constraints (ablation) | Diff · Paper | 3D reconstruction error | No clear effect |
| Use Diff rather than methods with stronger deformation constraints | NRSfM reconstruction · NRSfM Challenge | mean depth error | Helped |
| Use Diff rather than Pa17 | NRSfM reconstruction · dense, high-quality correspondences | reconstruction accuracy | Hurt |
| Use Diff rather than Pa17 | NRSfM reconstruction · Rug | 3D reconstruction error | Helped |
| Use Diff rather than Pa17 | NRSfM reconstruction · dense, high-quality correspondences | reconstruction accuracy | No clear effect |
Closest papers by meaning
- Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling (CVPR 2024 · similarity 0.86)
- Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching (CVPR 2024 · similarity 0.84)
- Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling (AAAI 2025 · similarity 0.84)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.84)
- Locally Orderless Images for Optimization in Differentiable Rendering (CVPR 2025 · similarity 0.84)
- Structure-from-Motion with a Non-Parametric Camera Model (CVPR 2025 · similarity 0.83)
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.