DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows

Abstract

The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and degradations that appear in real-world settings. We propose DeFlow, a method for learning stochastic image degradations from unpaired data. Our approach is based on a novel unpaired learning formulation for conditional normalizing flows. We model the degradation process in the latent space of a shared flow encoder-decoder network. This allows us to learn the conditional distribution of a noisy image given the clean input by solely minimizing the negative log-likelihood of the marginal distributions. We validate our DeFlow formulation on the task of joint image restoration and super-resolution. The models trained with the synthetic data generated by DeFlow outperform previous learnable approaches on all three datasets.

Publication
In Conference on Computer Vision and Pattern Recognition, CVPR 2021
Andreas Lugmayr
Andreas Lugmayr
PhD Student, ETH Zurich
Martin Danelljan
Martin Danelljan
Researcher

Researcher in Computer Vision and Machine Learning at ETH Zurich

Related