Research map / Point clouds / Registration and matching
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration
Yuxin Yao, Bailin Deng, Junhui Hou, 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 |
|---|---|---|---|
| use symmetrized point-to-plane instead of point-to-point distance (ablation) | SPARE · AMA handstand | Corr_err: 2.91 -> 0.38 | Improved |
| use symmetrized point-to-plane instead of point-to-plane distance (ablation) | SPARE · AMA handstand | Corr_err: 0.56 -> 0.38 | Improved |
| use symmetrized point-to-plane instead of point-to-plane distance (ablation) | SPARE · SHREC'20 | Corr_err: 1.76 -> 1.47 | Improved |
| use symmetrized point-to-plane instead of point-to-plane distance (ablation) | SPARE · AMA march1 | Corr_err: 0.09 -> 0.03 | Hurt |
| add adaptive robust weights (ablation) | SPARE · AMA handstand | Corr_err: 0.75 -> 0.38 | Improved |
| add adaptive robust weights (ablation) | SPARE · Partial data | Corr_err: 1.35 -> 0.46 | Improved |
| add adaptive robust weights (ablation) | SPARE · SHREC'20 | Corr_err: 1.89 -> 1.47 | Improved |
| use soft Gaussian weights instead of hard thresholding (ablation) | SPARE · AMA handstand | Corr_err: 0.63 -> 0.38 | Improved |
| use adaptive weights instead of Welsch robust loss (ablation) | SPARE · SHREC'20 | Corr_err: 1.53 -> 1.47 | Improved |
| use adaptive weights instead of Huber robust loss (ablation) | SPARE · Partial data | Corr_err: 0.78 -> 0.46 | Improved |
| use closed-form MM rotation update instead of steepest descent or L-BFGS (ablation) | SPARE · bunnyQ_Attack1 (DT4D) | convergence | Improved |
| decrease overlap ratio from 76.30% to 48.61% | AMM · AMA crane partial overlap | Corr_err: 0.79 -> 2.00 | Hurt |
Closest papers by meaning
- Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization (TPAMI 2023 · similarity 0.90)
- An Efficient Globally Optimal Algorithm for Asymmetric Point Matching (TPAMI 2016 · similarity 0.88)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.87)
- Fast and Robust Iterative Closest Point (TPAMI 2021 · similarity 0.87)
- Quasi-Newton Solver for Robust Non-Rigid Registration (CVPR 2020 · similarity 0.87)
- Minimal Solvers for 3D Scan Alignment With Pairs of Intersecting Lines (CVPR 2020 · 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.
