Person image generation through graph-based and appearance-decomposed generative adversarial network

Due to the sophisticated entanglements for non-rigid deformation, generating person images from source pose to target pose is a challenging work. In this paper, we present a novel framework to generate person images with shape consistency and appearance consistency. The proposed framework leverages...

全面介紹

書目詳細資料

發表在:	PeerJ Computer Science
Main Authors:	Yuling He, Yingding Zhao, Wenji Yang, Yilu Xu
格式:	Article
語言:	英语
出版:	PeerJ Inc. 2021-12-01
主題:	Image generation Generative adversarial network Graph network Pose transfer
在線閱讀:	https://peerj.com/articles/cs-761.pdf