Dual-task complementary networks for single-image deraining

• Published in: Signal, image and video processing Vol. 17; no. 8; pp. 4171 - 4179
• Main Authors: Zhang, Heng, Jia, Dongli, Han, Zixian
• Format: Journal Article
• Language: English
• Published: London Springer London 01.11.2023; Springer Nature B.V
• Subjects: Coders; Computer architecture; Computer Imaging; Computer Science; Encoders-Decoders; Image contrast; Image Processing and Computer Vision; Multimedia Information Systems; Original Paper; Pattern Recognition and Graphics; Rain; Signal,Image and Speech Processing; Similarity; Vision; Single-image deraining; Multiple losses; Progressive network; Multifeature fusion
• ISSN: 1863-1703; 1863-1711
• DOI: 10.1007/s11760-023-02649-1

Single-image rain removal is an extremely challenging task as it requires not only removing rain streaks with complex shapes, scales, and opacities but also recovering spatial details and high-level contextual structures of the underlying image. Although deep learning networks have achieved encouraging performance, current research mainly focuses on building deeper and more complex network architectures to recover reliable detailed textures or utilizing multi-scale encoder-decoder structures to learn semantic contexts in larger receptive fields, they are still not sufficient to balance rain streak removal and detail preservation. In this study, we propose a novel end-to-end network, called a dual-task complementary network (DTCN), composed of a detail recovery progressive network (DRPN) and a multifeature fusion encoder-decoder network (MEDN), to balance rain streak removal and detail preservation. Specifically, DRPN is designed to recover details in the original image, while MEDN is used to remove structural rain streaks. In addition, to reconstruct more natural and clear images, we integrate multiple network training losses, including structural similarity loss, perceptual contrast loss, perceptual image similarity loss, and edge loss. Experimental results demonstrate that our method outperforms several state-of-the-art methods on both synthetic and real rainy images. The code will be uploaded to https://github.com/zhang152267/DTCN .