Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences

dc.contributor.authorWang, T.
dc.contributor.authorVladimirov, K.
dc.contributor.authorGoh, S.
dc.contributor.authorLai, Y.-K.
dc.contributor.authorXie, X.
dc.contributor.authorTam, G. K. L.
dc.contributor.editorVidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.en_US
dc.date.accessioned2019-09-11T05:09:07Z
dc.date.available2019-09-11T05:09:07Z
dc.date.issued2019
dc.description.abstractSolving jigsaw puzzles is a classic problem in computer vision with various applications. Over the past decades, many useful approaches have been introduced. Most existing works use edge-wise similarity measures for assembling puzzles with square pieces of the same size, and recent work innovates to use the loop constraint to improve efficiency and accuracy. We observe that most existing techniques cannot be easily extended to puzzles with rectangular pieces of arbitrary sizes, and no existing loop constraints can be used to model such challenging scenarios. In this paper, we propose a new corner-wise matching approach, modelled using the MatchLift framework to solve square puzzles with cycle consistency. We further show one exciting example illustrating how puzzles with rectangular pieces of arbitrary sizes would be solved by our technique.en_US
dc.description.sectionheadersComputer Vision
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20191266
dc.identifier.isbn978-3-03868-096-3
dc.identifier.pages115-123
dc.identifier.urihttps://doi.org/10.2312/cgvc.20191266
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/cgvc20191266
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectImage comparison
dc.subjectApplied computing
dc.subjectImage composition
dc.subjectTheory of computation
dc.subjectSemidefinite programming
dc.titleRobust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondencesen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
115-123.pdf
Size:
16.55 MB
Format:
Adobe Portable Document Format