Unsupervised Template Warp Consistency for Implicit Surface Correspondences

Simple item page
dc.contributor.authorLiu, Mengyaen_US
dc.contributor.authorChhatkuli, Ajaden_US
dc.contributor.authorPostels, Janisen_US
dc.contributor.authorGool, Luc Vanen_US
dc.contributor.authorTombari, Federicoen_US
dc.contributor.editorMyszkowski, Karolen_US
dc.contributor.editorNiessner, Matthiasen_US
dc.date.accessioned2023-05-03T06:09:30Z
dc.date.available2023-05-03T06:09:30Z
dc.date.issued2023
dc.description.abstractUnsupervised template discovery via implicit representation in a category of shapes has recently shown strong performance. At the core, such methods deform input shapes to a common template space which allows establishing correspondences as well as implicit representation of the shapes. In this work we investigate the inherent assumption that the implicit neural field optimization naturally leads to consistently warped shapes, thus providing both good shape reconstruction and correspondences. Contrary to this convenient assumption, in practice we observe that such is not the case, consequently resulting in sub-optimal point correspondences. In order to solve the problem, we re-visit the warp design and more importantly introduce explicit constraints using unsupervised sparse point predictions, directly encouraging consistency of the warped shapes. We use the unsupervised sparse keypoints in order to further condition the deformation warp and enforce the consistency of the deformation warp. Experiments in dynamic non-rigid DFaust and ShapeNet categories show that our problem identification and solution provide the new state-of-the-art in unsupervised dense correspondences.en_US
dc.description.number2
dc.description.sectionheadersShape Correspondance
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14745
dc.identifier.issn1467-8659
dc.identifier.pages77-87
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14745
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14745
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.subjectCCS Concepts: Modelling -> Shape correspondences; Modeling -> Implicit surface reconstruction
dc.subjectModelling
dc.subjectShape correspondences
dc.subjectModeling
dc.subjectImplicit surface reconstruction
dc.titleUnsupervised Template Warp Consistency for Implicit Surface Correspondencesen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
v42i2pp077-087_cgf14745.pdf
Size:
8.94 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
paper1124_mm.pdf
Size:
4.51 MB
Format:
Adobe Portable Document Format
Download
Collections
42-Issue 2