Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning

arXiv:2012.05616v2 Announce Type: replace
Abstract: Human pose estimation (HPE) is a central part of understanding the visual narration and body movements of characters depicted in artwork collections, such as Greek vase paintings. Unfortunately, existing HPE methods do not generalise well across domains resulting in poorly recognized poses. Therefore, we propose a two step approach: (1) adapting a dataset of natural images of known person and pose annotations to the style of Greek vase paintings by means of image style-transfer. We …

abstract artwork arxiv characters cs.cv domains hpe human movements part style style transfer transfer transfer learning type understanding via visual