Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data

arXiv:2307.06737v2 Announce Type: replace
Abstract: Methods and datasets for human pose estimation focus predominantly on side- and front-view scenarios. We overcome the limitation by leveraging synthetic data and introduce RePoGen (RarE POses GENerator), an SMPL-based method for generating synthetic humans with comprehensive control over pose and view. Experiments on top-view datasets and a new dataset of real images with diverse poses show that adding the RePoGen data to the COCO dataset outperforms previous approaches to top- and bottom-view pose estimation …

arxiv cs.cv data human improving synthetic synthetic data type