Cross-view and Cross-pose Completion for 3D Human Understanding

arXiv:2311.09104v2 Announce Type: replace
Abstract: Human perception and understanding is a major domain of computer vision which, like many other vision subdomains recently, stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common pre-training strategy of relying on general purpose, object-centric image datasets such as ImageNet, is limited by an important domain shift. On the other hand, collecting domain-specific ground truth such as 2D or 3D labels does not scale well. …

abstract arxiv computer computer vision cs.cv datasets domain general human image image datasets large datasets large models major object perception pre-training strategy training type understanding view vision