期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 24, 期 -, 页码 1622-1636出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2021.3068833
关键词
Rain; Logic gates; Task analysis; Feature extraction; Visualization; History; Frequency-domain analysis; Rain removal; progressive network; diamond residual block; detail supplement
资金
- National Natural Science Foundation of China [62072218, 61862030]
- Natural Science Foundation of Jiangxi Province [20192ACB20002, 20192ACBL21008]
- Talent Project of Jiangxi Thousand Talents Program [jxsq2019201056]
This paper proposes an end-to-end rain removal network based on the progressive residual detail supplement method. By iterative design, it removes rain information from coarse to fine, retains more edge details, and achieves high-quality results for image denoising tasks.
Methods of rain removal based on deep learning have rapidly developed, and the image quality after rain removal is continuously improving. However, the results of most methods have some common problems, including a loss of details, a blurring of edges, and the existence of artifacts. To remove rain-related information more thoroughly and retain more edge details, this paper proposes an end-to-end rain removal network based on the progressive residual detail supplement (ERRN-PRDS) approach. The entire network structure is designed in an iterative manner to obtain higher-quality rain removal images from coarse to fine. In the network, a diamond residual block is constructed as the main module of iteration to learn the feature information of the background layer. Meanwhile, to keep more texture details in the background layer, a detail supplement mechanism is designed between the iterative layers to transfer more information to the next iterative operation. Experimental results show that this method can remove the rain information more completely and better retain the image edges compared with previous state-of-the-art methods. In addition, because of the sparsity of the detail injection, our network also achieves high-quality results for image denoising tasks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据