In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation. Unlike previous methods learning a rock-hard direct mapping between human bodies, we propose a new pathway to decompose the hard mapping into two more accessible subtasks, namely, semantic parsing transformation and appearance generation. Firstly, a semantic generative network is proposed to transform between semantic parsing maps, in order to simplify the non-rigid deformation learning. Secondly, an appearance generative network learns to synthesize semantic-aware textures. Thirdly, we demonstrate that training our framework in an end-to-end manner further refines the semantic maps and final results accordingly. Our method is generalizable to other semantic-aware person image generation tasks, eg, clothing texture transfer and controlled image manipulation. Experimental results demonstrate the superiority of our method on DeepFashion and Market-1501 datasets, especially in keeping the clothing attributes and better body shapes.
@article{arxiv.1904.03379,
title = {Unsupervised Person Image Generation with Semantic Parsing Transformation},
author = {Sijie Song and Wei Zhang and Jiaying Liu and Tao Mei},
journal= {arXiv preprint arXiv:1904.03379},
year = {2019}
}
Comments
Accepted to CVPR 2019 (Oral). Our project is available at https://github.com/SijieSong/person_generation_spt