Research map / 3D vision / Face and shape
Higher-Order Graph Principles towards Non-Rigid Surface Registration
Yun Zeng, Chaohui Wang, Xianfeng David Gu, Dimitris Samaras, Nikos Paragios A
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 |
|---|---|---|---|
| use higher-order graph registration instead of Kim et al. intrinsic method | dense surface registration · Body (Fig. 9) | average matching error: 0.2437 -> 0.0622 | Improved |
| use higher-order graph registration instead of Kim et al. | dense surface registration · Lion (Fig. 10) | average matching error: 0.1790 -> 0.0832 | Improved |
| use higher-order graph registration instead of Kim et al. | dense surface registration · Face (Fig. 11) | average matching error: 0.0465 -> 0.0319 | Improved |
| use higher-order graph registration instead of Kim et al. | dense surface registration · Face (Fig. 13) | average matching error: 0.0865 -> 0.0565 | Improved |
| use higher-order graph registration instead of Kim et al. | dense surface registration · Hand (Fig. 14) | average matching error: 0.1193 -> 0.0481 | Improved |
| use higher-order sparse matching instead of pairwise method [24] in full matching | sparse graph matching · synthetic sparse matching | percentage of correct matching / runtime: runs 2-10 times slower, degrades less sharply | Mixed |
| use our candidate selection with mid-edge uniformization instead of LSCM | dense surface matching · Face (Fig. 12) | flipped triangles: approximately 42 percent flipped triangles for LSCM | Improved |
Closest papers by meaning
- A Closest Point Proposal for MCMC-based Probabilistic Surface Registration (ECCV 2020 · similarity 0.87)
- Probabilistic Deformation Consistency for Unsupervised Shape Matching (AAAI 2026 · similarity 0.87)
- KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences (CVPR 2017 · similarity 0.87)
- Deformable Surface Tracking by Graph Matching (ICCV 2019 · similarity 0.87)
- Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration (CVPR 2023 · similarity 0.87)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · 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.
