Learning parallax attention for stereo image super-resolution

作     者：Wang, Longguang Wang, Yingqian Liang, Zhengfa Lin, Zaiping Yang, Jungang An, Wei Guo, Yulan 

作者机构：College of Electronic Science and Technology National University of Defense Technology China National Key Laboratory of Science and Technology on Blind Signal Processing China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2019年

核心收录：

主　　题：Optical resolving power 

摘      要：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. Copyright © 2019, The Authors. All rights reserved.