Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform. We in this paper propose the spontaneous motion estimation module, along with a refinement part, to learn attribute-driven deformation between source and target domains. Extensive experiments and visualization demonstrate effectiveness of these modules. We achieve promising results in unpaired-image translation tasks, and enable interesting applications based on spontaneous motion.
@article{arxiv.1907.01452,
title = {Attribute-Driven Spontaneous Motion in Unpaired Image Translation},
author = {Ruizheng Wu and Xin Tao and Xiaodong Gu and Xiaoyong Shen and Jiaya Jia},
journal= {arXiv preprint arXiv:1907.01452},
year = {2019}
}