Y-Net: Multi-Scale Feature Aggregation Network With Wavelet Structure Similarity Loss Function For Single Image Dehazing

• Main Authors: Yang, Hao-Hsiang, Yang, Chao-Han Huck, James Tsai, Yi-Chang
• Format: Conference Proceeding
• Language: English
• Subjects: discrete wavelet transform; Image reconstruction; multi-scale feature aggregation; Network architecture; Periodic structures; Signal processing algorithms; Signal reconstruction; Single image dehazing; Speech processing; structure similarity; Training; Y-net
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP40776.2020.9053920

Single image dehazing is the ill-posed two-dimensional signal reconstruction problem. Recently, deep convolutional neural networks (CNN) have been successfully used in many computer vision problems. In this paper, we propose a Y-net that is named for its structure. This network reconstructs clear images by aggregating multi-scale features maps. Additionally, we propose a Wavelet Structure SIMilarity (W-SSIM) loss function in the training step. In the proposed loss function, discrete wavelet transforms are applied repeatedly to divide the image into differently sized patches with different frequencies and scales. The proposed loss function is the accumulation of SSIM loss of various patches with respective ratios. Extensive experimental results demonstrate that the proposed Y-net with the W-SSIM loss function restores high-quality clear images and outperforms state-of-the-art algorithms. Code and models are available at https://github.com/dectrfov/Y-net.