Infrared and Laser Engineering, Volume. 51, Issue 6, 20210605(2022)
Multi-scale recurrent attention network for image motion deblurring
Figures & Tables(9)
Fig. 2. Encode，decode block. (a) Encode block; (b) Decode block; (c) End decode block; (d) Residual dense attention block
Fig. 3. (a), (b) Convolutional block attention submodule[15]; (c) Improved CBAM (CBAM-J)
Table 1. Connection modes of CBAM
View tableView in ArticleTable 1. Connection modes of CBAM
CBAM connections Output (y) Proposed(CBAM-J) $ x \cdot S(x) \cdot \left( {1+C\left( {x \cdot S(x)} \right)} \right) $ Channel+Spatial $ x \cdot C(x) \cdot S\left( {x \cdot C(x)} \right) $ Spatial+Channel $ x \cdot S(x) \cdot C\left( {x \cdot S(x)} \right) $ Spatial // Channel $ x \cdot S(x)+x \cdot C(x) $
Table 2. Deblurring evaluation results on three datasets
View tableView in ArticleTable 2. Deblurring evaluation results on three datasets
Method GoPro Lai Köhler SSIM PSNR/dB SSIM PSNR/dB SSIM PSNR/dB Proposed method 0.9185 29.0284 0.6674 16.5491 0.7625 19.9943 DeblurGAN 0.8474 25.0200 0.6425 15.8905 0.7447 19.7570 DeblurGAN-v2(Inception) 0.9141 28.2701 0.6514 16.1121 0.7469 19.4994 DeblurGAN-v2(MobileNet) 0.8731 25.9644 0.6598 16.4073 0.7556 19.7882 SRN deblur net 0.9331 30.1513 0.6494 16.1000 0.7505 19.5238
Table 3. Number of parameters & execution time per frame
View tableView in ArticleTable 3. Number of parameters & execution time per frame
Method FLOPs/G Size/MB Time/s Proposed method 261.19 12.3 0.206 DeblurGAN 678.29 45.6 0.694 DeblurGAN-v2(Inception) 411.34 244.7 0.212 DeblurGAN-v2(MobileNet) 43.75 13.6 0.068 SRN deblur net 1434.82 78.7 0.501
Tools
Get Citation
Copy Citation Text
Xiangjun Wang, Wensen Ouyang. Multi-scale recurrent attention network for image motion deblurring[J]. Infrared and Laser Engineering, 2022, 51(6): 20210605
Paper Information
Category: Image processing
Received: Aug. 10, 2021
Accepted: --
Published Online: Dec. 20, 2022
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20