Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation

Ying-Cong Chen, Xiaogang Xu, Zhuotao Tian, Jiaya Jia; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2408-2416

Abstract


Generative adversarial networks have achieved great success in unpaired image-to-image translation. Cycle consistency allows modeling the relationship between two distinct domains without paired data. In this paper, we propose an alternative framework, as an extension of latent space interpolation, to consider the intermediate region between two domains during translation. It is based on the fact that in a flat and smooth latent space, there exist many paths that connect two sample points. Properly selecting paths makes it possible to change only certain image attributes, which is useful for generating intermediate images between the two domains. We also show that this framework can be applied to multi-domain and multi-modal translation. Extensive experiments manifest its generality and applicability to various tasks.

Related Material


[pdf]
[bibtex]
@InProceedings{Chen_2019_CVPR,
author = {Chen, Ying-Cong and Xu, Xiaogang and Tian, Zhuotao and Jia, Jiaya},
title = {Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}