Addressing Domain Discrepancy: A Dual-branch Collaborative Model to Unsupervised Dehazing

TL;DR

This paper introduces a dual-branch collaborative model for unsupervised image dehazing that effectively reduces domain bias and improves detail preservation, achieving state-of-the-art results on benchmark datasets.

Contribution

The proposed DCM-dehaze model uniquely combines dual-branch architecture with contour constraints and feature enhancement to address domain bias in unsupervised dehazing.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively reduces domain bias in small-scale data.

Enhances image detail and clarity through novel modules.

Abstract

Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing model (DCM-dehaze) to address this issue. The proposed method consists of two collaborative branches: dehazing and contour constraints. Specifically, we design a dual depthwise separable convolutional module (DDSCM) to enhance the information expressiveness of deeper features and the correlation to shallow features. In addition, we construct a bidirectional contour function to optimize the edge features of the image to enhance the clarity and fidelity of the image details. Furthermore, we present feature enhancers via a residual dense architecture to eliminate redundant features of the dehazing process and further alleviate the domain deviation problem. Extensive experiments on benchmark datasets show that our method reaches the state-of-the-art. This project code will be available at \url{https://github.com/Fan-pixel/DCM-dehaze.