@inproceedings{54ed12854688460abd9a30dd0e21b9f3,
title = "Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation",
abstract = "Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation. Moreover, we propose a novel evaluation metric to properly measure the smoothness of latent style space of I2I translation models. The proposed method can be plugged in existing translation approaches, and our extensive experiments on different datasets show that it can significantly boost the quality of the generated images and the graduality of the interpolations.",
keywords = "Training, Interpolation, Computer vision, Smoothing methods, Protocols, Computational modeling, Semantics",
author = "Yahui Liu and Enver Sangineto and Yajing Chen and Linchao Bao and Haoxian Zhang and Nicu Sebe and Bruno Lepri and Wei Wang and Nadai, {Marco De}",
year = "2021",
month = nov,
day = "2",
doi = "10.1109/CVPR46437.2021.01064",
language = "English",
isbn = "9781665445108 (PoD)",
series = "Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE",
pages = "10780--10789",
booktitle = "2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
note = "2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) ; Conference date: 20-06-2021 Through 25-06-2021",
}