Analysis and Synthesis of 3D Shape Families via Deep-learned Generative Models of Surfaces

dc.contributor.authorHuang, Haibinen_US
dc.contributor.authorKalogerakis, Evangelosen_US
dc.contributor.authorMarlin, Benjaminen_US
dc.contributor.editorMirela Ben-Chen and Ligang Liuen_US
dc.date.accessioned2015-07-06T05:00:12Z
dc.date.available2015-07-06T05:00:12Z
dc.date.issued2015en_US
dc.description.abstractWe present a method for joint analysis and synthesis of geometrically diverse 3D shape families. Our method first learns part-based templates such that an optimal set of fuzzy point and part correspondences is computed between the shapes of an input collection based on a probabilistic deformation model. In contrast to previous template-based approaches, the geometry and deformation parameters of our part-based templates are learned from scratch. Based on the estimated shape correspondence, our method also learns a probabilistic generative model that hierarchically captures statistical relationships of corresponding surface point positions and parts as well as their existence in the input shapes. A deep learning procedure is used to capture these hierarchical relationships. The resulting generative model is used to produce control point arrangements that drive shape synthesis by combining and deforming parts from the input collection. The generative model also yields compact shape descriptors that are used to perform fine-grained classification. Finally, it can be also coupled with the probabilistic deformation model to further improve shape correspondence. We provide qualitative and quantitative evaluations of our method for shape correspondence, segmentation, fine-grained classification and synthesis. Our experiments demonstrate superior correspondence and segmentation results than previous state-of-the-art approaches.en_US
dc.description.number5en_US
dc.description.sectionheadersDescriptors and Shape Synthesisen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume34en_US
dc.identifier.doi10.1111/cgf.12694en_US
dc.identifier.pages025-038en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12694en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.3.5 [Computer Graphics]en_US
dc.subjectComputational Geometry and Object Modelingen_US
dc.titleAnalysis and Synthesis of 3D Shape Families via Deep-learned Generative Models of Surfacesen_US
Files