Laser & Optoelectronics Progress, Volume. 59, Issue 12, 1215001(2022)
Multiscale Feedforward Structure-Based Single Image Rain Removal Algorithm
Figures & Tables(11)
Fig. 4. Comparison of rain removal effects of different structures. (a) Real pictures; (b) rain pictures; (c) ResNet; (d) without MSRAS; (e) ours
Fig. 5. Rain removal effect diagram of different algorithms under the composite dataset. (a) Real pictures; (b) rain pictures; (c) DID-MDN; (d) JORDER; (e) RESCAN; (f) ours
Fig. 6. Rain removal renderings of different algorithms under real rain maps. (a) Real pictures; (b) DID-MDN; (c) JORDER; (d) RESCAN; (e) ours
Table 1. Parameter setting table of MSRAS
View tableTable 1. Parameter setting table of MSRAS
MSRAS Filter size Number of filters Number of output channels MSRAS1 16 48 16 16 MSRAS2 16 96 16 64 MSRAS3 16 96 16 64 MSRAS4 16 80 64
Table 2. Network parameter table
View tableTable 2. Network parameter table
Input size Filter size Number of filters Activation function Output Output size ［128，64，64，3］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ ‒ ‒ ‒ ［128，64，64，128］ ［128，64，64，128］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ ‒ ‒ ‒ ［128，64，64，128］ ［128，64，64，128］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ ‒ ‒ ‒ ［128，64，64，384］ ［128，64，64，384］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ 64 ReLU ［128，64，64，64］ ［128，64，64，64］ ‒ ‒ ‒ ［128，64，64，384］ ［128，64，64，384］ 16 ReLU ［128，64，64，16］ ［128，64，64，16］ 3 ReLU ［128，64，64，3］
Table 3. Quantitative values of rain removal effects of different structures
View tableTable 3. Quantitative values of rain removal effects of different structures
Picture SSIM Rain picture ResNet Without MSRAS Ours Photographer 0.7036 0.8915 0.8722 0.9443 Tiger 0.6968 0.8636 0.9057 0.9569 Cottage 0.7823 0.8932 0.9219 0.9788 Bridge 0.7733 0.8953 0.9032 0.9487 200 composite rain pictures 0.7135 0.8722 0.9063 0.9504 Picture PSNR /dB Rain picture ResNet Without MSRAS Ours Photographer 19.1911 27.9249 27.4652 33.6541 Tiger 20.0945 26.1495 28.5863 34.0457 Cottage 19.2886 26.3365 30.1487 34.2584 Bridge 18.6967 27.6713 28.9957 32.5586 200 composite rain pictures 18.3256 26.1841 28.9426 33.9953
Table 4. Quantitative values of rain removal effects of different algorithms under the composite dataset
View tableTable 4. Quantitative values of rain removal effects of different algorithms under the composite dataset
Picture SSIM DID-MDN JORDER RESCAN Ours Path 0.9069 0.9166 0.9389 0.9392 Model 0.8872 0.9233 0.9258 0.9473 Man 0.9022 0.9341 0.9389 0.9421 Arab 0.8575 0.9178 0.9498 0.9587 Rain100L 0.8821 0.9702 0.9752 0.9821 Rain100H 0.7285 0.7633 0.8726 0.8832 Rain800 0.8858 0.8835 0.8942 0.9289 Rain12000 0.8125 0.8325 0.8432 0.9072 Picture PSNR/dB DID-MDN JORDER RESCAN Ours Path 29.8813 30.0288 31.8564 32.0873 Model 28.1575 32.573 33.9847 34.2635 Man 31.2462 34.7834 35.1448 33.2516 Arab 27.1485 33.2175 35.5248 35.6874 Rain100L 25.6564 36.1143 36.2145 36.9326 Rain100H 17.8715 25.7412 26.4121 28.9627 Rain800 26.5586 25.9984 30.2486 31.7585 Rain12000 24.2263 25.8896 26.7423 28.9245
Table 5. Efficiency values of different algorithms
View tableTable 5. Efficiency values of different algorithms
Algorithm ResNet DID-MDN JORDER RESCAN Ours 6 pictures 140 70 66 57 31 200 pictures 7340 5665 4995 4740 3910
Tools
Get Citation
Copy Citation Text
Zhicheng Jiang, Zhiwei Li, Chen Chen, Jinxiang Zhou, Wuneng Zhou. Multiscale Feedforward Structure-Based Single Image Rain Removal Algorithm[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1215001
Paper Information
Category: Machine Vision
Received: Apr. 13, 2021
Accepted: Jun. 2, 2021
Published Online: May. 23, 2022
The Author Email: Zhiwei Li (zhiwei.li@sues.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20