We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An architecture that disentangles point cloud representation into feature space and 3D position space. 2) A position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors. 3) A repositioning technique that modifies the crosspoint-cloud relative positions. Ablation studies demonstrate the effectiveness of the above techniques. In rigid cases, Lepard combined with RANSAC and ICP demonstrates state-of-the-art registration recall of 93.9% / 71.3% on the 3DMatch / 3DLoMatch. In deformable cases, Lepard achieves +27.1% / +34.8% higher non-rigid feature matching recall than the prior art on our newly constructed 4DMatch / 4DLoMatch benchmark.
@article{arxiv.2111.12591,
title = {Lepard: Learning partial point cloud matching in rigid and deformable scenes},
author = {Yang Li and Tatsuya Harada},
journal= {arXiv preprint arXiv:2111.12591},
year = {2022}
}
Comments
Accepted to CVPR'2022. Code and data: https://github.com/rabbityl/lepard