Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing

TL;DR

This paper introduces a frequency domain diffusion model for unpaired image dehazing that leverages amplitude spectrum reconstruction and phase correction to improve dehazing quality without paired data.

Contribution

It proposes a novel frequency domain diffusion approach with amplitude residual encoding and phase correction, addressing limitations of contrastive learning methods in unpaired dehazing.

Findings

Outperforms state-of-the-art methods on synthetic datasets

Effective amplitude residual extraction improves dehazing quality

Phase correction reduces artifacts during dehazing

Abstract

Unpaired image dehazing has attracted increasing attention due to its flexible data requirements during model training. Dominant methods based on contrastive learning not only introduce haze-unrelated content information, but also ignore haze-specific properties in the frequency domain (\ie,~haze-related degradation is mainly manifested in the amplitude spectrum). To address these issues, we propose a novel frequency domain-based diffusion model, named \ours, for fully exploiting the beneficial knowledge in unpaired clear data. In particular, inspired by the strong generative ability shown by Diffusion Models (DMs), we tackle the dehazing task from the perspective of frequency domain reconstruction and perform the DMs to yield the amplitude spectrum consistent with the distribution of clear images. To implement it, we propose an Amplitude Residual Encoder (ARE) to extract the amplitude residuals, which effectively compensates for the amplitude gap from the hazy to clear domains, as well as provide supervision for the DMs training. In addition, we propose a Phase Correction Module (PCM) to eliminate artifacts by further refining the phase spectrum during dehazing with a simple attention mechanism. Experimental results demonstrate that our \ours outperforms other state-of-the-art methods on both synthetic and real-world datasets.