NDLI: Geometry and context guided refinement for stereo matching

Content Provider	IET Digital Library
Author	Zhang, Hong Li, Haojie Wang, Zhihui Yue, Yuxin Chen, Shenglun
Abstract	The disparity refinement phase of existing end-to-end stereo matching networks refines the disparity by learning the mapping from the concatenated coarse disparity and corresponding features to fine disparity. It depends on the scenarios' characteristics, such as the distribution of disparity and semantic categories contained in the domain, which makes the network fail to work on unseen domain. In this paper, we propose a geometry and context guided refinement network (GCGR-Net) containing a Fine Matching module and an Upsampling module. GCGR-Net learns to utilize pixels' relationship to get high resolution dense disparity, which is independent of the data's content. The Fine Matching module performs a minimum range search based on the relationship between the possible matching pixel pairs, i.e. the called geometry information, to recover the internal structure of the object. The Upsampling module obtains context information, the relationship between central pixel and the pixels in its neighborhood, to upsample the lower resolution disparity. The final disparity map is obtained step by step through an iterative refinement model. Experiment results show that our method not only has good performance in the training scenarios, but also outperforms previous methods on the unseen domain without fine-tuning.
Starting Page	2652
Ending Page	2659
Page Count	8
ISSN	17519659
Volume Number	14
e-ISSN	17519667
Issue Number	Issue 12, Oct (2020)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-ipr/14/12
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2019.1636
Journal	IET Image Processing
Publisher Date	2020-05-20
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Computer Vision And Image Processing Technique Concatenated Coarse Disparity Context Guided Refinement Context-guided Refinement Network Disparity Matching Phase Disparity Refinement Phase Domain Differences Existing End-to-end Stereo Matching Network Final Disparity Map Fine Disparity Fine Matching Module Fine-tuning GCGR-Net Learns Geometry Geometry Information High Resolution Dense Disparity Image Matching Image Recognition Image Resolution Iterative Method Iterative Refinement Model Knowledge Engineering Technique Learning in AI Lower Resolution Disparity Optical, Image And Video Signal Processing Pixel Possible Matching Pixel Pairs Refine Stereo Image Processing Stereo Matching Network Triangulation Principle Unseen Domain Unseen Scenes Upsampling Module Obtains Context Information
Content Type	Text
Resource Type	Article
Subject	Signal Processing Electrical and Electronic Engineering Computer Vision and Pattern Recognition Software

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

PatchMatch belief propagation meets depth upsampling for high-resolution depth maps

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

Stereo Matching with Spatiotemporal Disparity Refinement Using Simple Linear Iterative Clustering Segmentation

Stereo matching using cost volume fusion for high dynamic range scenes

Stereo matching based on segmented B-spline surface fitting and accelerated region belief propagation

Improving stereo matching by incorporating geometry prior into ConvNet

Estimation of disparity map of stereo image pairs using spatial domain local Gabor wavelet

Window-based approach for fast stereo correspondence

Local Stereo Matching with Improved Matching Cost and Disparity Refinement

Geometry and context guided refinement for stereo matching

Similar Documents

PatchMatch belief propagation meets depth upsampling for high-resolution depth maps

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

Stereo Matching with Spatiotemporal Disparity Refinement Using Simple Linear Iterative Clustering Segmentation

Stereo matching using cost volume fusion for high dynamic range scenes

Stereo matching based on segmented B-spline surface fitting and accelerated region belief propagation

Improving stereo matching by incorporating geometry prior into ConvNet

Estimation of disparity map of stereo image pairs using spatial domain local Gabor wavelet

Window-based approach for fast stereo correspondence

Local Stereo Matching with Improved Matching Cost and Disparity Refinement

Geometry and context guided refinement for stereo matching