Show simple item record

dc.contributor.authorMo, Kaichun
dc.contributor.authorGuerrero, Paul
dc.contributor.authorYi, Li
dc.contributor.authorSu, Hao
dc.contributor.authorWonka, Peter
dc.contributor.authorMitra, Niloy J.
dc.contributor.authorGuibas, Leonidas J.
dc.date.accessioned2021-03-28T06:21:45Z
dc.date.available2019-12-23T07:49:07Z
dc.date.available2021-03-28T06:21:45Z
dc.date.issued2020
dc.identifier.citationMo, K., Guerrero, P., Yi, L., Su, H., Wonka, P., Mitra, N. J., & Guibas, L. J. (2020). StructEdit: Learning Structural Shape Variations. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00888
dc.identifier.isbn978-1-7281-7169-2
dc.identifier.issn1063-6919
dc.identifier.doi10.1109/CVPR42600.2020.00888
dc.identifier.urihttp://hdl.handle.net/10754/660747
dc.description.abstractLearning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape, transferring edits from one shape to another, and for many other applications in 3D content creation. The common approach of encoding shapes as points in a high-dimensional latent feature space suggests treating shape differences as vectors in that space. Instead, we treat shape differences as primary objects in their own right and propose to encode them in their own latent space. In a setting where the shapes themselves are encoded in terms of fine-grained part hierarchies, we demonstrate that a separate encoding of shape deltas or differences provides a principled way to deal with inhomogeneities in the shape space due to different combinatorial part structures, while also allowing for compactness in the representation, as well as edit abstraction and transfer. Our approach is based on a conditional variational autoencoder for encoding and decoding shape deltas, conditioned on a source shape. We demonstrate the effectiveness and robustness of our approach in multiple shape modification and generation tasks, and provide comparison and ablation studies on the PartNet dataset, one of the largest publicly available 3D datasets.
dc.description.sponsorshipThis research was supported by NSF grant CHS-1528025, a Vannevar Bush Faculty Fellowship, KAUST Award No. OSR-CRG2017-3426, an ERC Starting Grant (SmartGeometry StG-2013-335373), ERC PoC Grant (SemanticCity), Google Faculty Awards, Google PhD Fellowships, Royal Society Advanced Newton Fellowship, and gifts from Adobe, Autodesk, Google, and the Dassault Foundation.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9156421/
dc.relation.urlhttps://arxiv.org/abs/1911.11098
dc.relation.urlhttps://arxiv.org/pdf/1911.11098.pdf
dc.relation.urlhttps://openaccess.thecvf.com/content_CVPR_2020/html/Mo_StructEdit_Learning_Structural_Shape_Variations_CVPR_2020_paper
dc.relation.urlhttps://openaccess.thecvf.com/content_CVPR_2020/papers/Mo_StructEdit_Learning_Structural_Shape_Variations_CVPR_2020_paper.pdf
dc.rightsArchived with thanks to IEEE
dc.titleStructEdit: Learning Structural Shape Variations
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.date13-19 June 2020
dc.conference.name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.locationSeattle, WA, USA
dc.eprint.versionPost-print
dc.contributor.institutionStanford University
dc.contributor.institutionAdobe Research
dc.contributor.institutionGoogle Research
dc.contributor.institutionUC San Diego
dc.contributor.institutionAdobe Research; University College London
dc.contributor.institutionStanford University; Facebook AI Research
dc.identifier.pages8856-8865
dc.identifier.arxivid1911.11098
kaust.personWonka, Peter
kaust.grant.numberOSR-CRG2017-3426
dc.identifier.eid2-s2.0-85094675507
refterms.dateFOA2019-12-23T07:50:07Z
kaust.acknowledged.supportUnitOSR


Files in this item

Thumbnail
Name:
Mo_StructEdit_Learning_Structural_Shape_Variations_CVPR_2020_paper.pdf
Size:
2.436Mb
Format:
PDF
Description:
Accepted Manuscript
Thumbnail
Name:
Mo_StructEdit_Learning_Structural_CVPR_2020_supplemental.pdf
Size:
8.457Mb
Format:
PDF
Description:
Supplementary Material

This item appears in the following Collection(s)

Show simple item record

VersionItemEditorDateSummary

*Selected version