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

TL;DR

DeFlow introduces a novel unpaired learning approach using conditional normalizing flows to model complex image degradations, enabling improved training data synthesis for image restoration and super-resolution tasks.

Contribution

It presents a new unpaired learning formulation for conditional flows that models degradation processes in latent space, advancing realistic data generation for image enhancement.

Findings

DeFlow outperforms previous methods on multiple datasets.

Synthetic data from DeFlow improves restoration and super-resolution results.

The approach effectively models complex degradations without paired data.

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 three recent datasets. Code and trained models are available at: https://github.com/volflow/DeFlow