Research map / Point clouds / Registration and matching
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet
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 PointNetLK instead of ICP | Point cloud registration · ModelNet40 test, unseen categories | rotation error: 175.51° -> 0.2° | Helped |
| Use PointNetLK instead of ICP | Point cloud registration · ModelNet40 test, unseen categories | translation error: 0.22 -> 10^{-4} | Helped |
| Use PointNetLK instead of Go-ICP | Point cloud registration · ModelNet40 test, unseen categories | registration time: 80.78s -> 0.2s | Helped |
| Replace max pooling with average pooling (ablation) | PointNetLK on noisy point clouds · ModelNet40, Gaussian noise | registration performance | Helped |
| Train with noisy data using average pooling (ablation) | PointNetLK · ModelNet40, Gaussian noise | registration performance | Helped |
| Train on partially visible data rather than full 3D data (ablation) | PointNetLK · ModelNet40, partially visible data | registration success | Helped |
Closest papers by meaning
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.88)
- PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations (AAAI 2024 · similarity 0.87)
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · similarity 0.87)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.87)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (AAAI 2025 · 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.