Conference paper Open Access

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation

Yahui Liu; Enver Sangineto; Yajing Chen; Linchao Bao; Haoxian Zhang; Nicu Sebe; Bruno Lepri; Wei Wang; Marco de Nadai

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.

IEEE/CVF International Conference on Computer Vision and Pattern Recognitiion, 2021, pages 10785-10794
All versions This version
Views 1111
Downloads 99
Data volume 61.0 MB61.0 MB
Unique views 1111
Unique downloads 99


Cite as