RUNet: A Robust UNet Architecture for Image Super-Resolution
Abstract
Single image super-resolution (SISR) is a challenging ill-posed problem which aims to restore or infer a high-resolution image from a low-resolution one. Powerful deep learning-based techniques have achieved state-of-the-art performance in SISR; however, they can underperform when handling images with non-stationary degradations, such as for the application of projector resolution enhancement. In this paper, a new UNet architecture that is able to learn the relationship between a set of degraded low-resolution images and their corresponding original high-resolution images is proposed. We propose employing a degradation model on training images in a non-stationary way, allowing the construction of a robust UNet (RUNet) for image super-resolution (SR). Experimental results show that the proposed RUNet improves the visual quality of the obtained super-resolution images while maintaining a low reconstruction error.
Cite
Text
Hu et al. "RUNet: A Robust UNet Architecture for Image Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00073Markdown
[Hu et al. "RUNet: A Robust UNet Architecture for Image Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/hu2019cvprw-runet/) doi:10.1109/CVPRW.2019.00073BibTeX
@inproceedings{hu2019cvprw-runet,
title = {{RUNet: A Robust UNet Architecture for Image Super-Resolution}},
author = {Hu, Xiaodan and Naiel, Mohamed A. and Wong, Alexander and Lamm, Mark and Fieguth, Paul W.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {505-507},
doi = {10.1109/CVPRW.2019.00073},
url = {https://mlanthology.org/cvprw/2019/hu2019cvprw-runet/}
}