Guided Real Image Dehazing using YCbCr Color Space

TL;DR

This paper introduces a novel dehazing network that leverages YCbCr color space features to improve haze removal in real-world images, supported by a new dataset and outperforming existing methods.

Contribution

The paper proposes the Structure Guided Dehazing Network (SGDN) utilizing YCbCr features and introduces the RW$^2$AH dataset for real-world haze dehazing.

Findings

SGDN outperforms state-of-the-art methods on real-world haze datasets.

Utilizing YCbCr features enhances structural guidance in dehazing.

The RW$^2$AH dataset provides diverse real-world haze images for training and evaluation.

Abstract

Image dehazing, particularly with learning-based methods, has gained significant attention due to its importance in real-world applications. However, relying solely on the RGB color space often fall short, frequently leaving residual haze. This arises from two main issues: the difficulty in obtaining clear textural features from hazy RGB images and the complexity of acquiring real haze/clean image pairs outside controlled environments like smoke-filled scenes. To address these issues, we first propose a novel Structure Guided Dehazing Network (SGDN) that leverages the superior structural properties of YCbCr features over RGB. It comprises two key modules: Bi-Color Guidance Bridge (BGB) and Color Enhancement Module (CEM). BGB integrates a phase integration module and an interactive attention module, utilizing the rich texture features of the YCbCr space to guide the RGB space, thereby recovering clearer features in both frequency and spatial domains. To maintain tonal consistency, CEM further enhances the color perception of RGB features by aggregating YCbCr channel information. Furthermore, for effective supervised learning, we introduce a Real-World Well-Aligned Haze (RW$^2$AH) dataset, which includes a diverse range of scenes from various geographical regions and climate conditions. Experimental results demonstrate that our method surpasses existing state-of-the-art methods across multiple real-world smoke/haze datasets. Code and Dataset: \textcolor{blue}{\url{https://github.com/fiwy0527/AAAI25_SGDN.}}