Please use this identifier to cite or link to this item:
Title: Left-Right Comparative Recurrent Model for Stereo Matching
Authors: Jie, Z
Wang, P 
Ling, Y
Zhao, B 
Wei, Y 
Feng, J 
Liu, W
Keywords: cs.CV
Issue Date: 14-Dec-2018
Publisher: IEEE
Citation: Jie, Z, Wang, P, Ling, Y, Zhao, B, Wei, Y, Feng, J, Liu, W (2018-12-14). Left-Right Comparative Recurrent Model for Stereo Matching. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 3838-3846. ScholarBank@NUS Repository.
Abstract: © 2018 IEEE. Leveraging the disparity information from both left and right views is crucial for stereo disparity estimation. Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the opposite view. However, the conventional left-right consistency check is an isolated post-processing step and heavily hand-crafted. This paper proposes a novel left-right comparative recurrent model to perform left-right consistency checking jointly with disparity estimation. At each recurrent step, the model produces disparity results for both views, and then performs online left-right comparison to identify the mismatched regions which may probably contain erroneously labeled pixels. A soft attention mechanism is introduced, which employs the learned error maps for better guiding the model to selectively focus on refining the unreliable regions at the next recurrent step. In this way, the generated disparity maps are progressively improved by the proposed recurrent model. Extensive evaluations on KITTI 2015, Scene Flow and Middlebury benchmarks validate the effectiveness of our model, demonstrating that state-of-the-art stereo disparity estimation results can be achieved by this new model.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN: 10636919
DOI: 10.1109/CVPR.2018.00404
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
1804.00796v1.pdfPublished version8.77 MBAdobe PDF




checked on Nov 23, 2020

Page view(s)

checked on Nov 27, 2020


checked on Nov 27, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.