Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform

arXiv:2404.11156v1 Announce Type: new
Abstract: Establishing accurate 3D correspondences between shapes stands as a pivotal challenge with profound implications for computer vision and robotics. However, existing self-supervised methods for this problem assume perfect input shape alignment, restricting their real-world applicability. In this work, we introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with Local Shape Transform, dubbed RIST, that learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. Specifically, RIST learns to dynamically formulate …

abstract alignment arxiv challenge computer computer vision cs.cv however novel pivotal robotics rotation semantic type via vision work world