Frequency Compensated Diffusion Model for Real-scene Dehazing

TL;DR

This paper introduces a frequency-compensated diffusion model with a novel spectral bias mitigation technique and a data augmentation pipeline, significantly improving real-world image dehazing performance.

Contribution

The paper proposes a Frequency Compensation block for diffusion models and a new haze augmentation method, enhancing generalization and detail recovery in real-world dehazing tasks.

Findings

Achieves superior perceptual and distortion metrics on real images.

Outperforms state-of-the-art dehazing methods.

Demonstrates effective generalization to real-world haze.

Abstract

Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze. First, we find that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is non-trivial. The spectral bias of deep networks hinders the higher frequency modes in Gaussian vectors from being learned and hence impairs the reconstruction of image details. To tackle this issue, we design a network unit, named Frequency Compensation block (FCB), with a bank of filters that jointly emphasize the mid-to-high frequencies of an input signal. We demonstrate that diffusion models with FCB achieve significant gains in both perceptual and distortion metrics. Second, to further boost the generalization performance, we propose a novel data synthesis pipeline, HazeAug, to augment haze in terms of degree and diversity. Within the framework, a solid baseline for blind dehazing is set up where models are trained on synthetic hazy-clean pairs, and directly generalize to real data. Extensive evaluations show that the proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images. Our code is at https://github.com/W-Jilly/frequency-compensated-diffusion-model-pytorch.