Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach

TL;DR

This paper introduces a diffusion-based method to synthesize realistic low-quality images from high-quality images, improving training data for real-world image restoration tasks by better matching real degradation distributions.

Contribution

The authors propose a novel diffusion model approach to generate more realistic LQ images for training, surpassing existing manual degradation models in realism and effectiveness.

Findings

Synthesized image pairs improve restoration model robustness.

Outperforms existing degradation models in experiments.

Effective for blind face restoration and super-resolution.

Abstract

In supervised image restoration tasks, one key issue is how to obtain the aligned high-quality (HQ) and low-quality (LQ) training image pairs. Unfortunately, such HQ-LQ training pairs are hard to capture in practice, and hard to synthesize due to the complex unknown degradation in the wild. While several sophisticated degradation models have been manually designed to synthesize LQ images from their HQ counterparts, the distribution gap between the synthesized and real-world LQ images remains large. We propose a new approach to synthesizing realistic image restoration training pairs using the emerging denoising diffusion probabilistic model (DDPM). First, we train a DDPM, which could convert a noisy input into the desired LQ image, with a large amount of collected LQ images, which define the target data distribution. Then, for a given HQ image, we synthesize an initial LQ image by using an off-the-shelf degradation model, and iteratively add proper Gaussian noises to it. Finally, we denoise the noisy LQ image using the pre-trained DDPM to obtain the final LQ image, which falls into the target distribution of real-world LQ images. Thanks to the strong capability of DDPM in distribution approximation, the synthesized HQ-LQ image pairs can be used to train robust models for real-world image restoration tasks, such as blind face image restoration and blind image super-resolution. Experiments demonstrated the superiority of our proposed approach to existing degradation models. Code and data will be released.