DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows
This addresses the bottleneck of obtaining paired training data for real-world image restoration applications, offering a novel method for synthetic data generation.
The paper tackles the problem of learning realistic image degradations from unpaired data to improve image restoration and super-resolution, achieving state-of-the-art performance on three recent datasets.
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