Identifying Style of 3D Shapes using Deep Metric Learning

dc.contributor.authorLim, Isaaken_US
dc.contributor.authorGehre, Anneen_US
dc.contributor.authorKobbelt, Leifen_US
dc.contributor.editorMaks Ovsjanikov and Daniele Panozzoen_US
dc.date.accessioned2016-06-17T14:12:08Z
dc.date.available2016-06-17T14:12:08Z
dc.date.issued2016en_US
dc.description.abstractWe present a method that expands on previous work in learning human perceived style similarity across objects with different structures and functionalities. Unlike previous approaches that tackle this problem with the help of hand-crafted geometric descriptors, we make use of recent advances in metric learning with neural networks (deep metric learning). This allows us to train the similarity metric on a shape collection directly, since any low- or high-level features needed to discriminate between different styles are identified by the neural network automatically. Furthermore, we avoid the issue of finding and comparing sub-elements of the shapes. We represent the shapes as rendered images and show how image tuples can be selected, generated and used efficiently for deep metric learning. We also tackle the problem of training our neural networks on relatively small datasets and show that we achieve style classification accuracy competitive with the state of the art. Finally, to reduce annotation effort we propose a method to incorporate heterogeneous data sources by adding annotated photos found online in order to expand or supplant parts of our training data.en_US
dc.description.number5en_US
dc.description.sectionheadersStructuresen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume35en_US
dc.identifier.doi10.1111/cgf.12977en_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages207-215en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12977en_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.subjectKeywordsen_US
dc.subjectstyle similarityen_US
dc.subjectdeep metric learningen_US
dc.titleIdentifying Style of 3D Shapes using Deep Metric Learningen_US
Files