Modular Latent Spaces for Shape Correspondences

dc.contributor.authorGanapathi-Subramanian, Vigneshen_US
dc.contributor.authorDiamanti, Olgaen_US
dc.contributor.authorGuibas, Leonidas J.en_US
dc.contributor.editorJu, Tao and Vaxman, Amiren_US
dc.date.accessioned2018-07-27T12:55:17Z
dc.date.available2018-07-27T12:55:17Z
dc.date.issued2018
dc.description.abstractWe consider the problem of transporting shape descriptors across shapes in a collection in a modular fashion, in order to establish correspondences between them. A common goal when mapping between multiple shapes is consistency, namely that compositions of maps along a cycle of shapes should be approximately an identity map. Existing attempts to enforce consistency typically require recomputing correspondences whenever a new shape is added to the collection, which can quickly become intractable. Instead, we propose an approach that is fully modular, where the bulk of the computation is done on each shape independently. To achieve this, we use intermediate nonlinear embedding spaces, computed individually on every shape; the embedding functions use ideas from diffusion geometry and capture how different descriptors on the same shape inter-relate. We then establish linear mappings between the different embedding spaces, via a shared latent space. The introduction of nonlinear embeddings allows for more nuanced correspondences, while the modularity of the construction allows for parallelizable calculation and efficient addition of new shapes. We compare the performance of our framework to standard functional correspondence techniques and showcase the use of this framework to simple interpolation and extrapolation tasks.en_US
dc.description.number5
dc.description.sectionheadersSpaces and Transformations
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume37
dc.identifier.doi10.1111/cgf.13502
dc.identifier.issn1467-8659
dc.identifier.pages199-210
dc.identifier.urihttps://doi.org/10.1111/cgf.13502
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13502
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.3.3 [Computer Graphics]
dc.subjectPicture/Image Generation
dc.subjectLine and curve generation
dc.titleModular Latent Spaces for Shape Correspondencesen_US
Files
Collections