Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

TL;DR

This paper introduces a novel cooperative unfolding network and an iterative mean-teacher framework for real-world image dehazing, effectively modeling atmospheric scattering and generating high-quality pseudo labels to improve dehazing performance.

Contribution

It presents the first RID-oriented iterative mean-teacher framework with coherence-based pseudo label generation, integrating physical models and deep learning for enhanced dehazing.

Findings

Achieves state-of-the-art results on RID benchmarks.

Effectively models atmospheric scattering and scene details.

Improves pseudo label quality using coherence-based selection.

Abstract

Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at https://github.com/cnyvfang/CORUN-Colabator.