Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces

• Published in: Computer graphics forum Vol. 34; no. 5; pp. 25 - 38
• Main Authors: Huang, Haibin, Kalogerakis, Evangelos, Marlin, Benjamin
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.08.2015
• Subjects: 3-D graphics; Analysis; Categories and Subject Descriptors (according to ACM CCS); Classification; Collection; Computer graphics; Correspondence; Deformation; I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling; Mathematical models; Probabilistic methods; Probability theory; Segmentation; Studies; Synthesis; Topological manifolds
• ISSN: 0167-7055; 1467-8659
• DOI: 10.1111/cgf.12694

We 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 mo...