We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain. In particular, we update both domain translation models simultaneously, and we generate target domain images by a denoising Markov Chain Monte Carlo approach that is conditioned on the input source domain images, based on Langevin dynamics. Our approach provides stable model training for image-to-image translation and generates high-quality image outputs. This enables state-of-the-art Fr\'echet Inception Distance (FID) performance on several public datasets, including both colour and multispectral imagery, significantly outperforming the contemporary adversarial image-to-image translation methods.
@article{arxiv.2104.05358,
title = {UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models},
author = {Hiroshi Sasaki and Chris G. Willcocks and Toby P. Breckon},
journal= {arXiv preprint arXiv:2104.05358},
year = {2021}
}