Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models

TL;DR

This paper introduces a semi-supervised image dehazing approach that combines Expectation-Maximization with Bidirectional Brownian Bridge Diffusion Models, effectively utilizing unpaired data and structural priors to improve dehazing performance.

Contribution

The paper proposes a novel two-stage semi-supervised dehazing method using EM and diffusion models, incorporating a new Residual Difference Convolution block for enhanced detail capture.

Findings

Achieves superior or comparable results to state-of-the-art methods

Effectively utilizes unpaired data for dehazing

Enhances detail preservation with RDC block

Abstract

Existing dehazing methods deal with real-world haze images with difficulty, especially scenes with thick haze. One of the main reasons is the lack of real-world paired data and robust priors. To avoid the costly collection of paired hazy and clear images, we propose an efficient semi-supervised image dehazing method via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models (EM-B3DM) with a two-stage learning scheme. In the first stage, we employ the EM algorithm to decouple the joint distribution of paired hazy and clear images into two conditional distributions, which are then modeled using a unified Brownian Bridge diffusion model to directly capture the structural and content-related correlations between hazy and clear images. In the second stage, we leverage the pre-trained model and large-scale unpaired hazy and clear images to further improve the performance of image dehazing. Additionally, we introduce a detail-enhanced Residual Difference Convolution block (RDC) to capture gradient-level information, significantly enhancing the model's representation capability. Extensive experiments demonstrate that our EM-B3DM achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.