Unsupervised Cycle-consistent Deformation for Shape Matching

dc.contributor.authorGroueix, Thibaulten_US
dc.contributor.authorFisher, Matthewen_US
dc.contributor.authorKim, Vladimir G.en_US
dc.contributor.authorRussel, Bryan C.en_US
dc.contributor.authorAubry, Mathieuen_US
dc.contributor.editorBommes, David and Huang, Huien_US
dc.date.accessioned2019-07-11T06:19:30Z
dc.date.available2019-07-11T06:19:30Z
dc.date.issued2019
dc.description.abstractWe propose a self-supervised approach to deep surface deformation. Given a pair of shapes, our algorithm directly predicts a parametric transformation from one shape to the other respecting correspondences. Our insight is to use cycle-consistency to define a notion of good correspondences in groups of objects and use it as a supervisory signal to train our network. Our method combines does not rely on a template, assume near isometric deformations or rely on point-correspondence supervision. We demonstrate the efficacy of our approach by using it to transfer segmentation across shapes. We show, on Shapenet, that our approach is competitive with comparable state-of-the-art methods when annotated training data is readily available, but outperforms them by a large margin in the few-shot segmentation scenario.en_US
dc.description.number5
dc.description.sectionheadersSynthesis and Learning
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume38
dc.identifier.doi10.1111/cgf.13794
dc.identifier.issn1467-8659
dc.identifier.pages123-133
dc.identifier.urihttps://doi.org/10.1111/cgf.13794
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13794
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleUnsupervised Cycle-consistent Deformation for Shape Matchingen_US
Files
Collections