Show simple item record

dc.contributor.authorSung, Minhyuken_US
dc.contributor.authorDubrovina, Anastasiaen_US
dc.contributor.authorKim, Vladimir G.en_US
dc.contributor.authorGuibas, Leonidas J.en_US
dc.contributor.editorJu, Tao and Vaxman, Amiren_US
dc.date.accessioned2018-07-27T12:54:35Z
dc.date.available2018-07-27T12:54:35Z
dc.date.issued2018
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.13492
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13492
dc.description.abstractModeling relations between components of 3D objects is essential for many geometry editing tasks. Existing techniques commonly rely on labeled components, which requires substantial annotation effort and limits components to a dictionary of predefined semantic parts. We propose a novel framework based on neural networks that analyzes an uncurated collection of 3D models from the same category and learns two important types of semantic relations among full and partial shapes: complementarity and interchangeability. The former helps to identify which two partial shapes make a complete plausible object, and the latter indicates that interchanging two partial shapes from different objects preserves the object plausibility. Our key idea is to jointly encode both relations by embedding partial shapes as fuzzy sets in dual embedding spaces. We model these two relations as fuzzy set operations performed across the dual embedding spaces, and within each space, respectively. We demonstrate the utility of our method for various retrieval tasks that are commonly needed in geometric modeling interfaces.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectShape modeling
dc.subjectMachine learning approaches
dc.subjectShape analysis
dc.titleLearning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spacesen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersShape Analysis and Representation
dc.description.volume37
dc.description.number5
dc.identifier.doi10.1111/cgf.13492
dc.identifier.pages71-81


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • 37-Issue 5
    Geometry Processing 2018 - Symposium Proceedings

Show simple item record