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.

Lepard 是一种基于学习的部分点云匹配方法，可以在刚性和可变形场景中进行匹配，其关键特征是利用三维位置知识实现点云匹配，通过特征空间和三维位置空间分离表示，显式地利用向量点积作为位置编码方法，并且采用重新定位技术改善交叉点云相对位置，与 RANSAC 和 ICP 结合应用于刚性场景中，Lepard 具有 93.9％/71.3％的顶尖匹配性能，优于先前的匹配方法，并且在可变形场景中提高了 + 27.1％/ +34.8％的非刚性特征匹配召回率，优于现有方法。