Laser & Optoelectronics Progress, Volume. 57, Issue 22, 221018(2020)
Image Denoising Based on Asymmetric Convolutional Neural Networks
Fig. 1. Partially synthesized noise images.
Fig. 2. CBDNet model
Fig. 3. CBDNet denoising subnet architecture
Fig. 4. UNet++ architecture
Fig. 5. Improved network model
Fig. 6. Denoising results of image 1. (a) Original image; (b) noise image; (c) CBDNet; (d) improved CBDNet
Fig. 7. Denoising results of image 2. (a) Original image; (b) noise image; (c) CBDNet; (d) improved CBDNet
Fig. 8. Denoising results of image 3. (a) Original image; (b) noise image; (c) CBDNet; (d) improved CBDNet
|
|
|
Get Citation
Copy Citation Text
Jianwang Gan, Yun Sha, Guoying Zhang. Image Denoising Based on Asymmetric Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221018
Category: Image Processing
Received: Apr. 2, 2020
Accepted: Apr. 21, 2020
Published Online: Nov. 5, 2020
The Author Email: Sha Yun (shayun@bipt.edu.cn)