Hourglass stereo matching network

Dan Jiang; Kai Yang; Yong Wang; Jinlong Li; Jingyi Xi; Wan Jiang

doi:10.1117/12.2653194

15 December 2022 Hourglass stereo matching network

Dan Jiang, Kai Yang, Yong Wang, Jinlong Li, Jingyi Xi, Wan Jiang

Proceedings Volume 12478, Thirteenth International Conference on Information Optics and Photonics (CIOP 2022); 124781D (2022) https://doi.org/10.1117/12.2653194
Event: Thirteenth International Conference on Information Optics and Photonics (CIOP 2022), 2022, Xi'an, China

Abstract

Although the deep learning-based stereo matching networks have made significant progress, the ability to find corresponding relationships in ill-conditioned regions (weak textures, repeated textures, occluded regions, etc.) still needs to be improved. Aiming at the above problems, an hourglass stereo matching network is proposed, which is mainly composed of an hourglass structure. The first is the hourglass feature extraction module, which uses the information of the global context to obtain more detailed features; then the obtained feature information is aggregated together to construct a cost volume. In the three-dimensional convolution module, multiple hourglass structures are used to refine disparity and use intermediate supervision to standardize the cost volume. It fuses the information again and makes better use of global context information. Finally obtain the disparity map through disparity regression. Through the verification test on the Scene Flow and KITTI dataset, it shows that the proposed method maintains better performance while reducing parameters, significantly reduces the error in ill-conditioned regions, and achieves competitive results.

Citation Download Citation

Dan Jiang, Kai Yang, Yong Wang, Jinlong Li, Jingyi Xi, and Wan Jiang "Hourglass stereo matching network", Proc. SPIE 12478, Thirteenth International Conference on Information Optics and Photonics (CIOP 2022), 124781D (15 December 2022); https://doi.org/10.1117/12.2653194

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available