UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models

• Published in: arXiv.org 2021-04
• Main Authors: Sasaki, Hiroshi, Willcocks, Chris G, Breckon, Toby P
• Format: Article
• Language: English
• Subjects: Color imagery; Diffusion; Domains; Image quality; Markov analysis; Markov chains; Noise reduction; Probabilistic models; Target recognition; Training
• ISSN: 2331-8422

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 Fréchet Inception Distance (FID) performance on several public datasets, including both colour and multispectral imagery, significantly outperforming the contemporary adversarial image-to-image translation methods.