Research map / Learning theory and algorithms / Matrix and tensor methods
Quasi-Newton Solver for Robust Non-Rigid Registration
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 the Welsch function for alignment and regularization instead of squared-error terms (ablation) | Robust non-rigid registration · Crane dataset | RMSE | Helped |
| Use gradually decreasing ν parameters instead of fixed ν parameters (ablation) | Robust non-rigid registration · Handstand, 42-th to 40-th mesh | RMSE | Helped |
| Reduce the deformation-graph sampling radius (ablation) | Robust non-rigid registration · Registration examples in the sampling-radius comparison | RMSE | Helped |
| Use PCA-ordered graph sampling instead of farthest-point sampling (ablation) | Robust non-rigid registration · Deformation-graph construction comparison | RMSE | No clear effect |
| Use the proposed method instead of N-ICP | MPI Faust · Mean over pose pairs | RMSE: 69.7 -> 10.2 | Helped |
| Use the proposed method instead of RPTS | MPI Faust · Mean over pose pairs | RMSE: 12.7 -> 10.2 | Helped |
| Use the proposed method instead of N-ICP | MPI Faust · Mean over pose pairs | time (s): 7.08 -> 1.30 | Helped |
| Use the proposed method instead of RPTS | MPI Faust · Mean over pose pairs | time (s): 34.86 -> 1.30 | Helped |
| Use the proposed method instead of other compared methods | Robust non-rigid registration · Partially overlapping bouncing data | RMSE | Helped |
| Use the proposed method instead of N-ICP and RPTS | Robust non-rigid registration · Noisy jumping data | RMSE | Helped |
Closest papers by meaning
- Non-Rigid Point Set Registration with Robust Transformation Estimation under Manifold Regularization (AAAI 2017 · similarity 0.86)
- Robust Outlier Rejection for 3D Registration With Variational Bayes (CVPR 2023 · similarity 0.85)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.85)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.85)
- Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis (CVPR 2024 · similarity 0.84)
- Progressive Correspondence Regenerator for Robust 3D Registration (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.