Learning Parallax Attention for Stereo Image Super-Resolution
Abstract
Stereo image pairs can be used to improve the performance of super-resolution (SR) since additional information is provided from a second viewpoint. However, it is challenging to incorporate this information for SR since disparities between stereo images vary significantly. In this paper, we propose a parallax-attention stereo superresolution network (PASSRnet) to integrate the information from a stereo image pair for SR. Specifically, we introduce a parallax-attention mechanism with a global receptive field along the epipolar line to handle different stereo images with large disparity variations. We also propose a new and the largest dataset for stereo image SR (namely, Flickr1024). Extensive experiments demonstrate that the parallax-attention mechanism can capture correspondence between stereo images to improve SR performance with a small computational and memory cost. Comparative results show that our PASSRnet achieves the state-of-the-art performance on the Middlebury, KITTI 2012 and KITTI 2015 datasets.
Cite
Text
Wang et al. "Learning Parallax Attention for Stereo Image Super-Resolution." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01253Markdown
[Wang et al. "Learning Parallax Attention for Stereo Image Super-Resolution." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/wang2019cvpr-learning-f/) doi:10.1109/CVPR.2019.01253BibTeX
@inproceedings{wang2019cvpr-learning-f,
title = {{Learning Parallax Attention for Stereo Image Super-Resolution}},
author = {Wang, Longguang and Wang, Yingqian and Liang, Zhengfa and Lin, Zaiping and Yang, Jungang and An, Wei and Guo, Yulan},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.01253},
url = {https://mlanthology.org/cvpr/2019/wang2019cvpr-learning-f/}
}