ChatPose: Chatting about 3D Human Pose

arXiv:2311.18836v2 Announce Type: replace
Abstract: We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description, a process that intertwines image interpretation, world knowledge, and an understanding of body language. Traditional human pose estimation and generation methods often operate in isolation, lacking semantic understanding and reasoning abilities. ChatPose …

abstract arxiv cs.cv framework human image images interpretation language language models large language large language models llms process reason textual type work