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

arXiv: https://arxiv.org/abs/1908.00274 · HTML: https://mlsanity.com/paper/1908.00274/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 4 of 4)

- [SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal](https://mlsanity.com/paper/2112.03631/) (2021)
- [Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth](https://mlsanity.com/paper/2405.17240/) (2024)
- [Prediction of low-keV monochromatic images from polyenergetic CT scans for improved automatic detection of pulmonary embolism](https://mlsanity.com/paper/2102.01445/) (2021)
- [Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models](https://mlsanity.com/paper/2409.06420/) (2024)

## Abstract (arXiv)

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. [Code release: https://github.com/ssarfraz/SPL]