Abstract
By the one-to-many nature of the super-resolution (SR) problem, a single low-resolution (LR) image can be mapped to many high-resolution (HR) images. However, learning based SR algorithms are trained to map an LR image to the corresponding ground truth (GT) HR image in the training dataset. The training loss will increase and penalize the algorithm when the output does not exactly match the GT target, even when the outputs are mathematically valid candidates according to the SR framework. This becomes more problematic for the blind SR, as diverse unknown blur kernels exacerbate the ill-posedness of the problem. To this end, we propose a fundamentally different approach for the SR by introducing the concept of the adaptive target. The adaptive target is generated from the original GT target by a transformation to match the output of the SR network. The adaptive target provides an effective way for the SR algorithm to deal with the ill-posed nature of the SR, by providing the algorithm with the flexibility of accepting a variety of valid solutions. Experimental results show the effectiveness of our algorithm, especially for improving the perceptual quality of HR outputs.
Original language | English |
---|---|
Title of host publication | Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 |
Publisher | IEEE Computer Society |
Pages | 16231-16240 |
Number of pages | 10 |
ISBN (Electronic) | 9781665445092 |
DOIs | |
Publication status | Published - 2021 |
Event | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States Duration: 2021 Jun 19 → 2021 Jun 25 |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
ISSN (Print) | 1063-6919 |
Conference
Conference | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 21/6/19 → 21/6/25 |
Bibliographical note
Funding Information:We proposed a novel way to deal with the ill-posed nature of SR by introducing the adaptive target. Our method can be applied to existing training data and network architectures without any modification, and without adding too much training time. We verified that our results outperform previous state-of-the-art methods, especially in generating perceptually pleasing images. For the blind SR, our method holds another advantage that no additional effort is required to find accurate blur kernels. In the future, we would like to extend our work to consider multi-frame for computing a new target. Additionally, we plan to extend our work for de-blurring as it inherently possesses the ill-posedness as well. Acknowledgement This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2014-3-00123, Development of High Performance Visual BigData Discovery Platform for Large-Scale Realtime Data Analysis, and No. 2020-0-01361, Artificial Intelligence Graduate School Program (Yonsei University)).
Publisher Copyright:
© 2021 IEEE
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition