The Shape Variational Autoencoder: A Deep Generative Model of Part-segmented 3D Objects

dc.contributor.authorNash, Charlieen_US
dc.contributor.authorWilliams, Chris K. I.en_US
dc.contributor.editorBærentzen, Jakob Andreas and Hildebrandt, Klausen_US
dc.date.accessioned2017-07-02T17:37:41Z
dc.date.available2017-07-02T17:37:41Z
dc.date.issued2017
dc.description.abstractWe introduce a generative model of part-segmented 3D objects: the shape variational auto-encoder (ShapeVAE). The ShapeVAE describes a joint distribution over the existence of object parts, the locations of a dense set of surface points, and over surface normals associated with these points. Our model makes use of a deep encoder-decoder architecture that leverages the partdecomposability of 3D objects to embed high-dimensional shape representations and sample novel instances. Given an input collection of part-segmented objects with dense point correspondences the ShapeVAE is capable of synthesizing novel, realistic shapes, and by performing conditional inference enables imputation of missing parts or surface normals. In addition, by generating both points and surface normals, our model allows for the use of powerful surface-reconstruction methods for mesh synthesis. We provide a quantitative evaluation of the ShapeVAE on shape-completion and test-set log-likelihood tasks and demonstrate that the model performs favourably against strong baselines. We demonstrate qualitatively that the ShapeVAE produces plausible shape samples, and that it captures a semantically meaningful shape-embedding. In addition we show that the ShapeVAE facilitates mesh reconstruction by sampling consistent surface normals.en_US
dc.description.number5
dc.description.sectionheadersDesign and Segmentation
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.13240
dc.identifier.issn1467-8659
dc.identifier.pages001-012
dc.identifier.urihttps://doi.org/10.1111/cgf.13240
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13240
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.3.5 [Computer Graphics]
dc.subjectComputational Geometry and Object Modelling
dc.titleThe Shape Variational Autoencoder: A Deep Generative Model of Part-segmented 3D Objectsen_US
Files
Collections