Xiangjun Wang, Wensen Ouyang. Multi-scale recurrent attention network for image motion deblurring[J]. Infrared and Laser Engineering, 2022, 51(6): 20210605
- Infrared and Laser Engineering
- Vol. 51, Issue 6, 20210605 (2022)
Fig. 1. Multi-scale recurrent Neural Network Architecture
Fig. 2. Encode，decode block. (a) Encode block; (b) Decode block; (c) End decode block; (d) Residual dense attention block
![(a), (b) Convolutional block attention submodule[15]; (c) Improved CBAM (CBAM-J)](/Images/icon/loading.gif){kind=icon}
Fig. 3. (a), (b) Convolutional block attention submodule[15]; (c) Improved CBAM (CBAM-J)
Fig. 4. CBAM connection modes in literature[15]
Fig. 5. Test result on Lai real blur dataset
Fig. 6. Test result on GoPro testing set
|
Table 1. Connection modes of CBAM
| ||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 2. Deblurring evaluation results on three datasets
|
Table 3. Number of parameters & execution time per frame
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20