Sen WANG, Yang ZHU, Yinhui ZHANG, Qingjian WANG, Zifen HE. Multi-stage frame alignment video super- resolution network[J]. Optics and Precision Engineering, 2023, 31(16): 2430
- Optics and Precision Engineering
- Vol. 31, Issue 16, 2430 (2023)
Fig. 1. Architecture of MSVSR
Fig. 2. Deblurring stage
Fig. 3. Pre-aligned module
Fig. 4. Sub-module in deblurring stage
Fig. 5. Shift-MLP module
Fig. 6. Feature fusion block
Fig. 7. Alignment stage［28］
Fig. 8. Reconstruction stage
Fig. 9. Performance and model complexity comparison on Vid4 dataset for BD task
Fig. 10. Qualitative comparison on REDS4［10］
Fig. 11. Qualitative comparison on Vid4［10］
Fig. 12. Qualitative comparison on Vimeo-90K-T［10］
Fig. 13. Comparison of temporal profile
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 1. Quantitative comparison［10］
|
Table 2. Ablation tests on Vid4 dataset for BD task
|
Table 3. Quantitative comparison of different convolution decomposition approaches on Vid4 dataset for BD task
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