WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning

TL;DR

This paper introduces WTCL-Dehaze, a semi-supervised image dehazing method that combines wavelet transform and contrastive learning to improve clarity and detail restoration in hazy images.

Contribution

It proposes a novel semi-supervised dehazing network integrating contrastive loss with wavelet transform for better feature extraction and generalization.

Findings

Outperforms state-of-the-art dehazing methods on benchmark datasets

Demonstrates robustness on real-world hazy images

Effectively utilizes both labeled and unlabeled data

Abstract

Images captured in hazy outdoor conditions often suffer from colour distortion, low contrast, and loss of detail, which impair high-level vision tasks. Single image dehazing is essential for applications such as autonomous driving and surveillance, with the aim of restoring image clarity. In this work, we propose WTCL-Dehaze an enhanced semi-supervised dehazing network that integrates Contrastive Loss and Discrete Wavelet Transform (DWT). We incorporate contrastive regularization to enhance feature representation by contrasting hazy and clear image pairs. Additionally, we utilize DWT for multi-scale feature extraction, effectively capturing high-frequency details and global structures. Our approach leverages both labelled and unlabelled data to mitigate the domain gap and improve generalization. The model is trained on a combination of synthetic and real-world datasets, ensuring robust performance across different scenarios. Extensive experiments demonstrate that our proposed algorithm achieves superior performance and improved robustness compared to state-of-the-art single image dehazing methods on both benchmark datasets and real-world images.