Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss

Saquib Sarfraz (Karlsruhe Institute of Technology), Constantin Seibold (Karlsruhe Institute of Technology), Haroon Khalid (Karlsruhe Institute of Technology), Rainer Stiefelhagen (Karlsruhe Institute of Technology)

Abstract
Generative adversarial networks has emerged as a defacto standard for image translation problems. To successfully drive such models, one has to rely on additional networks e.g., discriminators and/or perceptual networks. Training these networks with pixel based losses alone are generally not sufficient to learn the target distribution. In this paper, we propose a novel method of computing the loss directly between the source and target images that enable proper distillation of shape/content and colour/style. We show that this is useful in typical image-to-image translations allowing us to successfully drive the generator without relying on additional networks. We demonstrate this on many difficult image translation problems such as image-to-image domain mapping, single image super-resolution and photo realistic makeup transfer. Our extensive evaluation shows the effectiveness of the proposed formulation and its ability to synthesize realistic images.

DOI
10.5244/C.33.145
https://dx.doi.org/10.5244/C.33.145

Files
Paper (PDF)
Supplementary material (PDF)

BibTeX