GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration

TL;DR

This paper introduces GenDeg, a diffusion-based method for synthesizing diverse degradation patterns to improve the generalization of image restoration models across various real-world scenarios.

Contribution

The paper presents a novel diffusion model for generating diverse degradations and creates a large-scale dataset that enhances out-of-distribution performance of restoration models.

Findings

Models trained on the new dataset outperform those trained on existing datasets in real-world scenarios.

GenDeg synthesizes over 550k samples across six degradation types.

The approach improves generalization in all-in-one image restoration tasks.

Abstract

Deep learning-based models for All-In-One Image Restoration (AIOR) have achieved significant advancements in recent years. However, their practical applicability is limited by poor generalization to samples outside the training distribution. This limitation arises primarily from insufficient diversity in degradation variations and scenes within existing datasets, resulting in inadequate representations of real-world scenarios. Additionally, capturing large-scale real-world paired data for degradations such as haze, low-light, and raindrops is often cumbersome and sometimes infeasible. In this paper, we leverage the generative capabilities of latent diffusion models to synthesize high-quality degraded images from their clean counterparts. Specifically, we introduce GenDeg, a degradation and intensity-aware conditional diffusion model capable of producing diverse degradation patterns on clean images. Using GenDeg, we synthesize over 550k samples across six degradation types: haze, rain, snow, motion blur, low-light, and raindrops. These generated samples are integrated with existing datasets to form the GenDS dataset, comprising over 750k samples. Our experiments reveal that image restoration models trained on the GenDS dataset exhibit significant improvements in out-of-distribution performance compared to those trained solely on existing datasets. Furthermore, we provide comprehensive analyses on implications of diffusion model-based synthetic degradations for AIOR.