Unsupervised Template-assisted Point Cloud Shape Correspondence Network

Unsupervised point cloud shape correspondence aims to establish point-wise correspondences between source and target point clouds. Existing methods obtain correspon-dences directly by computing point-wise feature similar-ity between point clouds. However, non-rigid objects pos-sess strong deformability and unusual shapes, making it a longstanding challenge to directly establish correspon-dences between point clouds with unconventional shapes. To address this challenge, we propose an unsupervised Template-Assisted point cloud shape correspondence Net-work, termed TANet, including a template generation mod-ule and a template assistance module. The proposed TANet enjoys several merits. Firstly, the template generation mod-ule establishes a set of learnable templates with explicit structures. Secondly, we introduce a template assistance module that extensively leverages the generated templates to establish more accurate shape correspondences from multiple perspectives. Extensive experiments on four hu-man and animal datasets demonstrate that TANet achieves favorable performance against state-of-the-art methods.

1. Introduction

Point cloud shape correspondence is a challenging task that identifies and densely matches the source and target point clouds with deformable 3D shapes. The task has significant implications for various industries, including augmented re-ality [1], gaming [15], and robotics [21], [32]. However, the unrestricted mobility of humans and animals and their un-usual postures have made direct correspondence between unconventional shapes a longstanding challenge in point cloud shape correspondence.