Research map / Point clouds / Registration and matching
PointNetLK Revisited
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 |
|---|---|---|---|
| replace the numerical finite-difference Jacobian with a fully analytical, decomposed Jacobian | PointNetLK · ModelNet40 and ShapeNetCore unseen categories | rotation RMSE (deg.): ModelNet40: 8.183 -> 3.350; ShapeNetCore: 12.941 -> 3.983 | Helped |
| add voxelization at test time, using 8 voxels and 500 points per voxel (ablation) | Analytical PointNetLK · 3DMatch | rotation RMSE (degrees): 15.996 -> 7.165 | Helped |
| add voxelization at test time, using 27 voxels and 148 points per voxel (ablation) | Analytical PointNetLK · 3DMatch | translation RMSE (m): 0.738 -> 0.308 | Helped |
| use 8 voxels with 1,000 points per voxel instead of 8 voxels with 500 points (ablation) | Analytical PointNetLK · 3DMatch | translation median (m): 0.105 -> 0.096 | Helped |
| train on ModelNet40 and test directly on 3DMatch using voxelization | Analytical PointNetLK · 3DMatch | rotation RMSE (degrees): 15.996 -> 7.165 | Helped |
Closest papers by meaning
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.88)
- Unlocking Generalization Power in LiDAR Point Cloud Registration (CVPR 2025 · similarity 0.88)
- HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions (AAAI 2025 · similarity 0.88)
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.88)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (AAAI 2025 · similarity 0.88)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.88)
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.