Research map / 3D vision / Face and shape
Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization
Yuxin Yao, Bailin Deng, Weiwei Xu, Juyong Zhang
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 |
|---|---|---|---|
| Ours vs RPTS on handstand | Ours · handstand | mean RMSE (x1e-2): 3.30 -> 1.21 | Improved |
| Ours vs RPTS time on handstand | Ours · handstand | average time (s): 215.47 -> 1.70 | Improved |
| Ours vs best baseline on MPI Faust | Ours · MPI Faust | mean RMSE (x1e-3): 29.56 -> 11.44 | Improved |
| Ours vs N-ICP time on MPI Faust | Ours · MPI Faust | mean time (s): 1.47 -> 0.58 | Improved |
| Ours vs RPTS under 50% sparse noise | Ours · jumping sparse noise 50% | mean RMSE (x1e-2): 5.37 -> 5.23 | Improved |
| Ours vs RPTS on DeepDeform | Ours · DeepDeform | mean r_s (x1e-2): 6.49 -> 6.49 | No clear effect |
| Ours vs NDP on DeepDeform median | Ours · DeepDeform | median r_s (x1e-2): 1.86 -> 1.93 | Hurt |
| Ours vs SyNoRiM on DeepDeform time | Ours · DeepDeform | average time (s): 0.56 -> 1.39 | Hurt |
| replace Welsch function with squared l2-norm (ablation) | Ours · partial overlap crane/samba | RMSE | Improved |
| use dynamic update of Welsch parameters instead of fixed values (ablation) | Ours · partial overlap crane/samba | RMSE | Improved |
| use smaller deformation graph radius R (ablation) | Ours · MPI Faust | alignment accuracy | Mixed |
| use Anderson acceleration and quadratic surrogate over L-BFGS inner solver (ablation) | Ours · jumping | convergence speed | Improved |
Closest papers by meaning
- Quasi-Newton Solver for Robust Non-Rigid Registration (CVPR 2020 · similarity 0.93)
- SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration (TPAMI 2025 · similarity 0.90)
- Fast and Robust Iterative Closest Point (TPAMI 2021 · similarity 0.89)
- Efficient and Robust Registration on the 3D Special Euclidean Group (ICCV 2019 · similarity 0.89)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.88)
- Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis (CVPR 2024 · similarity 0.87)
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.
