Lightweight Pyramid Networks for Image Deraining

• Published in: IEEE transaction on neural networks and learning systems 2020-06, Vol.31 (6), p.1794-1807
• Main Authors: Fu, Xueyang, Liang, Borong, Huang, Yue, Ding, Xinghao, Paisley, John
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer vision; Deep convolutional neural network (CNN); Electronic devices; Feature extraction; image pyramid; Knowledge engineering; Laplace equations; Learning; Learning systems; Lightweight; lightweight networks; Neural networks; Parameters; Rain; rain removal; residual learning; Task analysis
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2019.2926481

Existing deep convolutional neural networks (CNNs) have found major success in image deraining, but at the expense of an enormous number of parameters. This limits their potential applications, e.g., in mobile devices. In this paper, we propose a lightweight pyramid networt (LPNet) for single-image deraining. Instead of designing a complex network structure, we use domain-specific knowledge to simplify the learning process. In particular, we find that by introducing the mature Gaussian-Laplacian image pyramid decomposition technology to the neural network, the learning problem at each pyramid level is greatly simplified and can be handled by a relatively shallow network with few parameters. We adopt recursive and residual network structures to build the proposed LPNet, which has less than 8K parameters while still achieving the state-of-the-art performance on rain removal. We also discuss the potential value of LPNet for other low- and high-level vision tasks.