Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
Yiqun Mei, Yuchen Fan, Yuqian Zhou, Lichao Huang, Thomas S. Huang, Honghui Shi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 5690-5699
Abstract
Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existing works have ignored the long-range feature-wise similarities in natural images. Some recent works have successfully leveraged this intrinsic feature correlation by exploring non-local attention modules. However, none of the current deep models have studied another inherent property of images: cross-scale feature correlation. In this paper, we propose the first Cross-Scale Non-Local (CS-NL) attention module with integration into a recurrent neural network. By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image. The performance of SISR is significantly improved by exhaustively integrating all possible priors. Extensive experiments demonstrate the effectiveness of the proposed CS-NL module by setting new state-of-the-arts on multiple SISR benchmarks.
Related Material
[pdf]
[supp]
[arXiv]
[video]
[
bibtex]
@InProceedings{Mei_2020_CVPR,
author = {Mei, Yiqun and Fan, Yuchen and Zhou, Yuqian and Huang, Lichao and Huang, Thomas S. and Shi, Honghui},
title = {Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}