Selective Wavelet Attention Learning for Single Image Deraining

• Published in: International journal of computer vision 2021-04, Vol.129 (4), p.1282-1300
• Main Authors: Huang, Huaibo, Yu, Aijing, Chai, Zhenhua, He, Ran, Tan, Tieniu
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Coders; Computer Imaging; Computer Science; Image Processing and Computer Vision; Image restoration; Pattern Recognition; Pattern Recognition and Graphics; Rain; Separation; Special Issue on Computer Vision for All Seasons: Adverse Weather and Lighting Conditions; Vision; Wavelet transforms
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-020-01421-z

Single image deraining refers to the process of restoring the clean background scene from a rainy image. Current approaches have resorted to deep learning techniques to remove rain from a single image by leveraging some prior information. However, due to the various appearances of rain streaks and accumulation, it is difficult to separate rain and background information in the embedding space, which results in inaccurate deraining. To address this issue, this paper proposes a selective wavelet attention learning method by learning a series of wavelet attention maps to guide the separation of rain and background information in both spatial and frequency domains. The key aspect of our method is utilizing wavelet transform to learn the content and structure of rainy features because the high-frequency features are more sensitive to rain degradations, whereas the low-frequency features preserve more of the background content. To begin with, we develop a selective wavelet attention encoder–decoder network to learn wavelet attention maps guiding the separation of rainy and background features at multiple scales. Meanwhile, we introduce wavelet pooling and unpooling to the encoder–decoder network, which shows superiority in learning increasingly abstract representations while preserving the background details. In addition, we propose latent alignment learning to supervise the background features as well as augment the training data to further improve the accuracy of deraining. Finally, we employ a hierarchical discriminator network based on selective wavelet attention to adversarially improve the visual fidelity of the generated results both globally and locally. Extensive experiments on synthetic and real datasets demonstrate that the proposed approach achieves more appealing results both quantitatively and qualitatively than the recent state-of-the-art methods.