Abstract
In stereo image super-resolution (SR), exploiting both intra-view and cross-view information is significant but challenging. As existing single image SR (SISR) methods are powerful in intra-view information exploitation, in this letter, we propose a generic stereo attention module (SAM) to extend arbitrary SISR networks for stereo image SR. Specifically, we apply two identical pretrained SISR networks to stereo images. The extracted stereo features at different stages are fed to SAMs to interact cross-view information. Finally, the intra-view and cross-view information is incorporated by SISR networks for stereo image SR. Experiments on the KITTI2012 , KITTI2015 and Middlebury datasets have demonstrated the effectiveness of our scheme. Using SAM, we can exploit cross-view information while maintaining the superiority of intra-view information exploitation, resulting in notable performance gain to SISR networks. Moreover, SRResNet equipped with our SAM outperforms the state-of-the-art stereo SR methods. Source code is available at https://github.com/XinyiYing/SAM .
Highlights
Stereo correspondence and image SR are jointly learned using a parallax attention mechanism [12]. These existing stereo image SR methods have used cross-view information, their performance is still inferior to some single image SR (SISR) methods (e.g., EDSR [14], RCAN [15]) due to the inferiority in intra-view information exploitation
We address the aforementioned challenges by proposing a stereo attention module (SAM) for stereo image SR
The main contributions of this letter can be summarized as follows: 1) We propose a generic module to extend pretrianed SISR networks for stereo image SR
Summary
Xinyi Ying , Yingqian Wang , Longguang Wang , Weidong Sheng, Wei An, and Yulan Guo. Abstract—In stereo image super-resolution (SR), exploiting both intra-view and cross-view information is significant but challenging. As existing single image SR (SISR) methods are powerful in intra-view information exploitation, in this letter, we propose a generic stereo attention module (SAM) to extend arbitrary SISR networks for stereo image SR. We apply two identical pretrained SISR networks to stereo images. The extracted stereo features at different stages are fed to SAMs to interact cross-view information. The intra-view and cross-view information is incorporated by SISR networks for stereo image SR. Using SAM, we can exploit cross-view information while maintaining the superiority of intra-view information exploitation, resulting in notable performance gain to SISR networks.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
