Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models

TL;DR

This paper introduces a frequency-aware guidance loss for diffusion models that improves blind image restoration by enforcing content consistency in both spatial and frequency domains, leading to better quality results.

Contribution

The authors propose a novel frequency-aware guidance loss based on 2D discrete wavelet transform, enhancing diffusion models for blind image restoration tasks.

Findings

Achieves a 3.72 dB PSNR improvement in image deblurring.

Effectively reduces distortion and enhances image details.

Demonstrates superior performance across multiple blind restoration tasks.

Abstract

Blind image restoration remains a significant challenge in low-level vision tasks. Recently, denoising diffusion models have shown remarkable performance in image synthesis. Guided diffusion models, leveraging the potent generative priors of pre-trained models along with a differential guidance loss, have achieved promising results in blind image restoration. However, these models typically consider data consistency solely in the spatial domain, often resulting in distorted image content. In this paper, we propose a novel frequency-aware guidance loss that can be integrated into various diffusion models in a plug-and-play manner. Our proposed guidance loss, based on 2D discrete wavelet transform, simultaneously enforces content consistency in both the spatial and frequency domains. Experimental results demonstrate the effectiveness of our method in three blind restoration tasks: blind image deblurring, imaging through turbulence, and blind restoration for multiple degradations. Notably, our method achieves a significant improvement in PSNR score, with a remarkable enhancement of 3.72\,dB in image deblurring. Moreover, our method exhibits superior capability in generating images with rich details and reduced distortion, leading to the best visual quality.