Taming Diffusion Models for Image Restoration: A Review

TL;DR

This review paper discusses how diffusion models are used for image restoration tasks like denoising and deblurring, highlighting recent techniques, challenges, and future directions in the field.

Contribution

It provides a comprehensive survey of diffusion model applications in image restoration, summarizing key methods, challenges, and future research opportunities.

Findings

Diffusion models significantly improve image restoration quality.

Current frameworks face challenges like computational cost and model stability.

Future work should focus on efficiency and robustness enhancements.

Abstract

Diffusion models have achieved remarkable progress in generative modelling, particularly in enhancing image quality to conform to human preferences. Recently, these models have also been applied to low-level computer vision for photo-realistic image restoration (IR) in tasks such as image denoising, deblurring, dehazing, etc. In this review paper, we introduce key constructions in diffusion models and survey contemporary techniques that make use of diffusion models in solving general IR tasks. Furthermore, we point out the main challenges and limitations of existing diffusion-based IR frameworks and provide potential directions for future work.