Unsupervised Stereo Matching with Surface Normal Assistance for Indoor Depth Estimation
Author:
Fan Xiule1ORCID, Amiri Ali Jahani2, Fidan Baris1ORCID, Jeon Soo1ORCID
Affiliation:
1. Department of Mechanical and Mechatronics Engineering, University of Waterloo, 200 University Ave. W., Waterloo, ON N2L 3G1, Canada 2. Avidbots Corp., 45 Washburn Dr., Kitchener, ON N2R 1S1, Canada
Abstract
To obtain more accurate depth information with stereo cameras, various learning-based stereo-matching algorithms have been developed recently. These algorithms, however, are significantly affected by textureless regions in indoor applications. To address this problem, we propose a new deep-neural-network-based data-driven stereo-matching scheme that utilizes the surface normal. The proposed scheme includes a neural network and a two-stage training strategy. The neural network involves a feature-extraction module, a normal-estimation branch, and a disparity-estimation branch. The training processes of the feature-extraction module and the normal-estimation branch are supervised while the training of the disparity-estimation branch is performed unsupervised. Experimental results indicate that the proposed scheme is capable of estimating the surface normal accurately in textureless regions, leading to improvement in the disparity-estimation accuracy and stereo-matching quality in indoor applications involving such textureless regions.
Funder
Mitacs Avidbots Corp
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference56 articles.
1. Local Disparity Estimation With Three-Moded Cross Census and Advanced Support Weight;Lee;IEEE Trans. Multimed.,2013 2. Kolmogorov, V., and Zabih, R. (2001, January 7–14). Computing visual correspondence with occlusions using graph cuts. Proceedings of the IEEE International Conference on Computer Vision, Vancouver, BC, Canada. 3. Stereo Processing by Semiglobal Matching and Mutual Information;Hirschmuller;IEEE Trans. Pattern Anal. Mach. Intell.,2008 4. Mei, X., Sun, X., Zhou, M., Jiao, S., Wang, H., and Zhang, X. (2011, January 6–13). On building an accurate stereo matching system on graphics hardware. Proceedings of the IEEE International Conference on Computer Vision Workshops, Barcelona, Spain. 5. Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., and Bry, A. (2017, January 22–29). End-to-End Learning of Geometry and Context for Deep Stereo Regression. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.
|
|