Compensation Atmospheric Scattering Model and Two-Branch Network for Single Image Dehazing

• Published in: IEEE transactions on emerging topics in computational intelligence Vol. 8; no. 4; pp. 2880 - 2896
• Main Authors: Wang, Xudong, Chen, Xi'ai, Ren, Weihong, Han, Zhi, Fan, Huijie, Tang, Yandong, Liu, Lianqing
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Atmospheric modeling; Atmospheric scattering; atmospheric scattering model; Compensation; Computational modeling; Feature extraction; Image dehazing; Image enhancement; image restoration; Labels; Lighting; Modules; Scattering; Semi-supervised learning; Synthetic data; Training
• ISSN: 2471-285X; 2471-285X
• DOI: 10.1109/TETCI.2024.3386838

Most existing dehazing networks rely on synthetic hazy-clear image pairs for training, and thus fail to work well in real-world scenes. In this paper, we deduce a reformulated atmospheric scattering model for a hazy image and propose a novel lightweight two-branch dehazing network. In the model, we use a Transformation Map to represent the dehazing transformation and use a Compensation Map to represent variable illumination compensation. Based on this model, we design a T wo- B ranch N etwork (TBN) to jointly estimate the Transformation Map and Compensation Map. Our TBN is designed with a shared Feature Extraction Module and two Adaptive Weight Modules. The Feature Extraction Module is used to extract shared features from hazy images. The two Adaptive Weight Modules generate two groups of adaptive weighted features for the Transformation Map and Compensation Map, respectively. This design allows for a targeted conversion of features to the Transformation Map and Compensation Map. To further improve the dehazing performance in the real-world, we propose a semi-supervised learning strategy for TBN. Specifically, by performing supervised pre-training based on synthetic image pairs, we propose a Self-Enhancement method to generate pseudo-labels, and then further train our TBN with the pseudo-labels in a semi-supervised way. Extensive experiments demonstrate that the model-based TBN outperforms the state-of-the-art methods on various real-world datasets.