Zheng XU, Jiaheng HE, Yanqi WANG, Xiaodong WANG, Tongqun REN. End-to-end deblurring model for microscopic vision[J]. Optics and Precision Engineering, 2024, 32(20): 3047
- Optics and Precision Engineering
- Vol. 32, Issue 20, 3047 (2024)
Fig. 1. Workflow of end-to-end deblurring model
Fig. 2. Process workflow of frequency domain
Fig. 3. Architecture of the blur discriminator.
Fig. 4. Architecture of deblurring network
Fig. 5. Comparison between gaussian blur kernel size and optical defocus distance
Fig. 6. Images with different blurriness degrees
Fig. 7. Overall training process
Fig. 8. Comparison of restoration results
Fig. 9. Recovery of image with multiple blurriness
Fig. 10. Experimental parts for precision measurement
|
Table 1. Blurriness discrimination results
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 2. Frequency domain processing module ablation experiment
| |||||||||||||||||||||||||||||
Table 3. Recovery result of corresponding branch networks for different degrees of blurriness
|
Table 4. SSIM scores of end-to-end deblurring model
|
Table 5. Recovery result on fine-tuned datasets
|
Table 6. Comparison experiment of discriminator
|
Table 7. Comparison experiment of deblurring networks
|
Table 8. Comparison experiment of detection accuracy
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