FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restoration

TL;DR

FDG-Diff is a novel frequency-domain-guided diffusion framework that effectively restores compressed hazy images by incorporating frequency information, a specialized compensation module, and adaptive denoising, outperforming existing methods.

Contribution

The paper introduces FDG-Diff, a new dehazing framework that leverages frequency-domain guidance, a high-frequency compensation module, and a degradation-aware denoising predictor for improved compressed hazy image restoration.

Findings

Outperforms state-of-the-art dehazing methods on multiple datasets.

Effectively restores details in compressed hazy images.

Demonstrates robustness across various compression levels.

Abstract

In this study, we reveal that the interaction between haze degradation and JPEG compression introduces complex joint loss effects, which significantly complicate image restoration. Existing dehazing models often neglect compression effects, which limits their effectiveness in practical applications. To address these challenges, we introduce three key contributions. First, we design FDG-Diff, a novel frequency-domain-guided dehazing framework that improves JPEG image restoration by leveraging frequency-domain information. Second, we introduce the High-Frequency Compensation Module (HFCM), which enhances spatial-domain detail restoration by incorporating frequency-domain augmentation techniques into a diffusion-based restoration framework. Lastly, the introduction of the Degradation-Aware Denoising Timestep Predictor (DADTP) module further enhances restoration quality by enabling adaptive region-specific restoration, effectively addressing regional degradation inconsistencies in compressed hazy images. Experimental results across multiple compressed dehazing datasets demonstrate that our method consistently outperforms the latest state-of-the-art approaches. Code be available at https://github.com/SYSUzrc/FDG-Diff.