Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On

dc.contributor.authorVidaurre, Raquelen_US
dc.contributor.authorSantesteban, Igoren_US
dc.contributor.authorGarces, Elenaen_US
dc.contributor.authorCasas, Danen_US
dc.contributor.editorBender, Jan and Popa, Tiberiuen_US
dc.date.accessioned2020-10-16T06:25:37Z
dc.date.available2020-10-16T06:25:37Z
dc.date.issued2020
dc.description.abstractWe present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications.en_US
dc.description.number8
dc.description.sectionheadersData-Driven Cloth
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14109
dc.identifier.issn1467-8659
dc.identifier.pages145-156
dc.identifier.urihttps://doi.org/10.1111/cgf.14109
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14109
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectAnimation
dc.subjectMachine learning
dc.titleFully Convolutional Graph Neural Networks for Parametric Virtual Try-Onen_US
Files
Collections