Decomposition Makes Better Rain Removal: An Improved Attention-Guided Deraining Network

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 10; pp. 3981 - 3995
• Main Authors: Jiang, Kui, Wang, Zhongyuan, Yi, Peng, Chen, Chen, Han, Zhen, Lu, Tao, Huang, Baojin, Jiang, Junjun
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; attention mechanism; Complexity; Correlation; Decomposition; Deep learning; Estimation; Haze; Image deraining; Image restoration; layer-wise learning; Machine learning; Neural networks; non-local network; Rain; Raindrops; Self-similarity; Source code; Task analysis; Visual effects
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2020.3044887

Rain streaks in the air show diverse characteristics with different shapes, directions, densities, even the complex overlapped phenomenon, causing great challenges for the deraining task. Recently, deep learning based image deraining methods have been extensively investigated due to their excellent performance. However, most of the existing algorithms still have limitations in removing rain streaks while preserving rich textural details under complicated rain conditions. To this end, we propose to decompose rain streaks into multiple rain layers and individually estimate each of them along the network stages to cope with the increasing abstracts. To better characterize rain layers, an improved non-local block is designed to exploit the self-similarity of rain information by learning the holistic spatial feature correlations while reducing the calculation complexity. Moreover, a mixed attention mechanism is applied to guide the fusion of rain layers by focusing on the local and global overlaps among these rain layers. Extensive experiments on both synthetic rainy/rain-haze/raindrop datasets, real-world samples, the haze, and low-light scenarios show substantial improvements both on quantitative indicators and visual effects over the current state-of-the-art technologies. The source code is available at https://github.com/kuihua/IADN .