Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

arXiv:2403.13647v1 Announce Type: new
Abstract: Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE. Considering that human can quickly perceive potential keypoints of arbitrary objects, we propose a novel framework for CAPE based on such potential keypoints (named …

abstract arxiv cs.cv feature features image images meta query refine support type vectors