Show simple item record

dc.contributor.authorEzuz, Danielleen_US
dc.contributor.authorSolomon, Justinen_US
dc.contributor.authorKim, Vladimir G.en_US
dc.contributor.authorBen-Chen, Mirelaen_US
dc.contributor.editorBærentzen, Jakob Andreas and Hildebrandt, Klausen_US
dc.date.accessioned2017-07-02T17:37:46Z
dc.date.available2017-07-02T17:37:46Z
dc.date.issued2017
dc.identifier.issn1467-8659
dc.identifier.urihttp://dx.doi.org/10.1111/cgf.13244
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13244
dc.description.abstractDeep neural networks provide a promising tool for incorporating semantic information in geometry processing applications. Unlike image and video processing, however, geometry processing requires handling unstructured geometric data, and thus data representation becomes an important challenge in this framework. Existing approaches tackle this challenge by converting point clouds, meshes, or polygon soups into regular representations using, e.g., multi-view images, volumetric grids or planar parameterizations. In each of these cases, geometric data representation is treated as a fixed pre-process that is largely disconnected from the machine learning tool. In contrast, we propose to optimize for the geometric representation during the network learning process using a novel metric alignment layer. Our approach maps unstructured geometric data to a regular domain by minimizing the metric distortion of the map using the regularized Gromov-Wasserstein objective. This objective is parameterized by the metric of the target domain and is differentiable; thus, it can be easily incorporated into a deep network framework. Furthermore, the objective aims to align the metrics of the input and output domains, promoting consistent output for similar shapes. We show the effectiveness of our layer within a deep network trained for shape classification, demonstrating state-of-the-art performance for nonrigid shapes.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.3.5 [Computer Graphics]
dc.subjectComputational Geometry and Object Modeling
dc.subjectGeometric algorithms
dc.subjectlanguages
dc.subjectand systems
dc.titleGWCNN: A Metric Alignment Layer for Deep Shape Analysisen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersMaps and Parametrization
dc.description.volume36
dc.description.number5
dc.identifier.doi10.1111/cgf.13244
dc.identifier.pages049-057


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 36-Issue 5
    Geometry Processing 2017 - Symposium Proceedings

Show simple item record