Visual Attention Dehazing Network with Multi-level Features Refinement and Fusion. (October 2021)

• Record Type: Journal Article
• Authors: Yin, Shibai; Yang, Xiaolong; Wang, Yibin; Yang, Yee-Hong
• Is Part Of: Pattern recognition. Volume 118(2021)
• Publication Date: 2021-10
• Subjects: image dehazing -- attention mechanism -- multi-level features -- recurrent network; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108021
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: The proposed network contains a feature extraction network, a recurrent refinement network and an encoder-decoder network. The recurrent refinement network generates and refines the haze attention map using low-level and high-level features as input alternatively. The encoder-decoder network predicts the dehazing result with the guidance of a haze attention map and the fused multi-level features. Abstract: Image dehazing is very important for many computer vision tasks. However, typical CNN-based methods learn a direct mapping from a hazy image to a clear image, ignoring relevant haze priors and multi-level features. In this paper, a new Visual Attention Dehazing Network (VADN) with multi-level refinement and fusion is proposed, which leverages a haze attention map as a haze relevant prior and learns complementary haze information among multi-level features. The VADN contains a feature extraction network, a recurrent refinement network and an encoder-decoder network. The feature extraction network captures the multi-level features. The recurrent refinement network generates and refines the haze attention map by taking low-level features and high-level features as inputs alternatively. Then, the haze attention map is injected into the encoder-decoder network to obtain the clear image with the help of complementary information learned from informative multi-level features. The experimental results demonstrate that the average PSNR of VADN is 32.50 dB which outperforms most state-of-the-art methods by up to 5.14 dB. Besides, the run time of VADN is 0.067 s, only 55 % of the run time spent by the recent enhanced pix2pix dehazing network.