Research map / Point clouds / Registration and matching
Lepard: Learning Partial Point Cloud Matching in Rigid and Deformable Scenes
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 Lepard instead of Predator | feature matching on 4DMatch · 4DMatch | NFMR: +27.1% | Helped |
| use Lepard instead of Predator | feature matching on 4DLoMatch · 4DLoMatch | NFMR: +34.8% | Helped |
| use Lepard instead of Predator with RANSAC and ICP | rigid point-cloud registration · 3DMatch | RR: 92.3 -> 93.9 | Helped |
| use Lepard instead of Predator with RANSAC and ICP | rigid point-cloud registration · 3DLoMatch | RR: 65.2 -> 71.3 | Helped |
| disentangle position and feature streams (ablation) | Lepard matching · 4DMatch | NFMR: 84.1 -> 83.7 | No clear effect |
| disentangle position and feature streams (ablation) | Lepard matching · 4DLoMatch | NFMR: 63.3 -> 66.9 | Helped |
| use relative instead of absolute sinusoidal positional encoding (ablation) | Lepard matching · 4DLoMatch | NFMR: +3.8% | Helped |
| add repositioning using the rigid fit (ablation) | Lepard matching · 4DMatch | NFMR: 80.8 -> 83.7; +2.9% | Helped |
| add repositioning using the rigid fit (ablation) | Lepard matching · 4DLoMatch | NFMR: 63.6 -> 66.9; +3.3% | Helped |
| replace dual-softmax matching with Sinkhorn (ablation) | Lepard matching · 4DMatch | NFMR: 83.7 -> 81.7 | Hurt |
| use random-rotation positioning instead of repositioning (ablation) | Lepard matching · 4DMatch | NFMR: 83.7 -> 79.2 | Hurt |
| increase warping loss weight from 0 to 0.1 (ablation) | Lepard deformable matching · 4DLoMatch | NFMR: 62.1 -> 66.9 | Helped |
Closest papers by meaning
- DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features (CVPR 2025 · similarity 0.89)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.87)
- Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model (CVPR 2025 · similarity 0.87)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (NeurIPS 2024 · similarity 0.86)
- Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension (CVPR 2024 · similarity 0.86)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · 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.