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

Abstract

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.

10 pages, 8 figures

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Denoising Diffusion Probabilistic Models
• Deep Residual Learning for Image Recognition
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• NICE: Non-linear Independent Components Estimation
• Generative Modeling by Estimating Gradients of the Data Distribution
• Toward Multimodal Image-to-Image Translation
• Searching for Activation Functions
• Unsupervised Image-to-Image Translation Networks
• Improved Denoising Diffusion Probabilistic Models
• Multimodal Unsupervised Image-to-Image Translation
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• Style Augmentation: Data Augmentation via Style Randomization
• Denoising Diffusion Implicit Models
• Image to Image Translation for Domain Adaptation

Cited by in corpus (5)

• Diffusion Models in Vision: A Survey
• Diffusion Model-Based Image Editing: A Survey
• Gotta Go Fast When Generating Data with Score-Based Models
• Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
• Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities