Learning a Single Network for Scale-Arbitrary Super-Resolution
Abstract
Recently, the performance of single image super-resolution (SR) has been significantly improved with powerful networks. However, these networks are developed for image SR with specific integer scale factors (e.g., x2/3/4), and cannot handle non-integer and asymmetric SR. In this paper, we propose to learn a scale-arbitrary image SR network from scale-specific networks. Specifically, we develop a plug-in module for existing SR networks to perform scale-arbitrary SR, which consists of multiple scale-aware feature adaption blocks and a scale-aware upsampling layer. Moreover, conditional convolution is used in our plug-in module to generate dynamic scale-aware filters, which enables our network to adapt to arbitrary scale factors. Our plug-in module can be easily adapted to existing networks to realize scale-arbitrary SR with a single model. These networks plugged with our module can produce promising results for non-integer and asymmetric SR while maintaining state-of-the-art performance for SR with integer scale factors. Besides, the additional computational and memory cost of our module is very small.
Cite
Text
Wang et al. "Learning a Single Network for Scale-Arbitrary Super-Resolution." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00476Markdown
[Wang et al. "Learning a Single Network for Scale-Arbitrary Super-Resolution." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/wang2021iccv-learning/) doi:10.1109/ICCV48922.2021.00476BibTeX
@inproceedings{wang2021iccv-learning,
title = {{Learning a Single Network for Scale-Arbitrary Super-Resolution}},
author = {Wang, Longguang and Wang, Yingqian and Lin, Zaiping and Yang, Jungang and An, Wei and Guo, Yulan},
booktitle = {International Conference on Computer Vision},
year = {2021},
pages = {4801-4810},
doi = {10.1109/ICCV48922.2021.00476},
url = {https://mlanthology.org/iccv/2021/wang2021iccv-learning/}
}