NDLI: Improving stereo matching by incorporating geometry prior into ConvNet

Content Provider	IET Digital Library
Author	Liang, Zhengfa Liu, Hengzhu Qiao, Linbo Feng, Yiliu Chen, Wei
Abstract	Deep learning-based methods for stereo matching have shown superior performance over traditional ones. However, most of them ignore the inherent geometry prior of stereo matching when training, i.e. the reference image can be reconstructed from the second image in the visible regions. The reconstruction can be achieved by backward warping the second image using the disparity map of the reference image, while the visible regions can be calculated by left-right consistency check. This prior is useful especially when the ground truth disparity is sparse (e.g. the outdoor scene such as KITTI 2015). This prior incorporated into a two-stage end-to-end training process, both of which try to minimise the end-point-error with respect to the sparse ground truth disparity (supervised learning), and the reconstruction error (self-supervised learning). The predicted disparity and the reconstruction error of the first stage act as additional information, and are fed to the second stage to make further use of this prior knowledge to improve performance. Experiments on the challenging KITTI 2015 dataset show that the method improves the results in the foreground region, and ranks first among all the published methods on the D1-fg metric.
Starting Page	1194
Ending Page	1196
Page Count	3
ISSN	00135194
Volume Number	53
e-ISSN	1350911X
Issue Number	Issue 17, Aug (2017)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/el/53/17
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/el.2017.2418
Journal	Electronics Letters
Publisher Date	2017-08-04
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Backward Warping Challenging KITTI 2015 Dataset Combinatorial Mathematics Computer Vision And Image Processing Technique ConvNet D1-fg Metric Deep Learning-based Method Disparity Map End-point-error Minimisation Foreground Region Geometry Image Matching Image Recognition Image Reconstruction Knowledge Engineering Technique Learning in AI Left-right Consistency Check Predicted Disparity Reconstruction Error Reference Image Self-supervised Learning Sparse Ground Truth Disparity Stereo Image Processing Stereo Matching Supervised Learning Two-stage End-to-end Training Process
Content Type	Text
Resource Type	Article
Subject	Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Geometry and context guided refinement for stereo matching

Research on joint segment optimisation and stereo matching

RESC-net: reconstruction error as skip connection for stereo matching

Improvement of disparity map refinement stage using adaptive least square plane fitting technique

Window-based approach for fast stereo correspondence

As-global-as-possible stereo matching with adaptive smoothness prior

Matching cost function using robust soft rank transformations

Asymmetric occlusion detection using linear regression and weight-based filling for stereo disparity map estimation

Augmented Lagrangian-based approach for dense three-dimensional structure and motion estimation from binocular image sequences

Improving stereo matching by incorporating geometry prior into ConvNet

Similar Documents

Geometry and context guided refinement for stereo matching

Research on joint segment optimisation and stereo matching

RESC-net: reconstruction error as skip connection for stereo matching

Improvement of disparity map refinement stage using adaptive least square plane fitting technique

Window-based approach for fast stereo correspondence

As-global-as-possible stereo matching with adaptive smoothness prior

Matching cost function using robust soft rank transformations

Asymmetric occlusion detection using linear regression and weight-based filling for stereo disparity map estimation

Augmented Lagrangian-based approach for dense three-dimensional structure and motion estimation from binocular image sequences

Improving stereo matching by incorporating geometry prior into ConvNet