Skip navigation
Skip navigation

PMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching

Li, Lincheng; zhang, Shunli; Yu, Xin; Zhang, Li

Description

Estimating the disparity and normal direction of one pixel simultaneously, instead of only disparity, also known as 3D label methods, can achieve much higher subpixel accuracy in the stereo matching problem. However, it is extremely difficult to assign an appropriate 3D label to each pixel from the continuous label space R3 while maintaining global consistency because of the infinite parameter space. In this paper, we propose a novel algorithm called PatchMatch-based superpixel cut to assign 3D...[Show more]

dc.contributor.authorLi, Lincheng
dc.contributor.authorzhang, Shunli
dc.contributor.authorYu, Xin
dc.contributor.authorZhang, Li
dc.date.accessioned2020-01-24T01:02:40Z
dc.identifier.issn1051-8215
dc.identifier.urihttp://hdl.handle.net/1885/199606
dc.description.abstractEstimating the disparity and normal direction of one pixel simultaneously, instead of only disparity, also known as 3D label methods, can achieve much higher subpixel accuracy in the stereo matching problem. However, it is extremely difficult to assign an appropriate 3D label to each pixel from the continuous label space R3 while maintaining global consistency because of the infinite parameter space. In this paper, we propose a novel algorithm called PatchMatch-based superpixel cut to assign 3D labels of an image more accurately. In order to achieve robust and precise stereo matching between local windows, we develop a bilayer matching cost, where a bottom-up scheme is exploited to design the two layers. The bottom layer is employed to measure the similarity between small square patches locally by exploiting a pretrained convolutional neural network, and then, the top layer is developed to assemble the local matching costs in large irregular windows induced by the tangent planes of object surfaces. To optimize the spatial smoothness of local assignments, we propose a novel strategy to update 3D labels. In the procedure of optimization, both segmentation information and random refinement of PatchMatch are exploited to update candidate 3D label set for each pixel with high probability of achieving lower loss. Since pairwise energy of general candidate label sets violates the submodular property of graph cut, we propose a novel multilayer superpixel structure to group candidate label sets into candidate assignments, which thereby can be efficiently fused by α-expansion graph cut. Extensive experiments demonstrate that our method can achieve higher subpixel accuracy in different data sets, and currently ranks first on the new challenging Middlebury 3.0 benchmark among all the existing methods.
dc.description.sponsorshipThis work was supported by the National Natural Science Foundation of China under Grant 61172125, Grant 61132007, and Grant U1533132
dc.format.mimetypeapplication/pdf
dc.language.isoen_AU
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.rights© 2016 IEEE
dc.sourceIEEE Transactions on Circuits and Systems for Video Technology
dc.subject3D label
dc.subjectPatchMatch
dc.subjectstereo matching
dc.subjectsuperpixel cut (SC)
dc.titlePMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume28
dcterms.dateAccepted2016-11-08
dc.date.issued2016-11-15
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationa383154xPUB9515
local.publisher.urlhttps://ieeexplore.ieee.org
local.type.statusPublished Version
local.contributor.affiliationLi, Lincheng, Tsinghua University
local.contributor.affiliationzhang, Shunli, Beijing Jiaotong University
local.contributor.affiliationYu, Xin, College of Engineering and Computer Science, ANU
local.contributor.affiliationZhang, Li, Tsinghua University
local.description.embargo2037-12-31
local.bibliographicCitation.issue3
local.bibliographicCitation.startpage679
local.bibliographicCitation.lastpage692
local.identifier.doi10.1109/TCSVT.2016.2628782
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2019-11-25T07:23:36Z
local.identifier.scopusID2-s2.0-85042916615
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Li_PMSC%3A_PatchMatch-Based_2018.pdf5.07 MBAdobe PDF    Request a copy


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

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator