Show simple item record

dc.contributor.authorDonati, Nicolas
dc.contributor.authorSharma, Abhishek
dc.contributor.authorOvsjanikov, Maks
dc.date.accessioned2020-04-09T07:18:51Z
dc.date.available2020-04-09T07:18:51Z
dc.date.issued2020-08-05
dc.identifier.citationDonati, N., Sharma, A., & Ovsjanikov, M. (2020). Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00862
dc.identifier.isbn9781728171685
dc.identifier.doi10.1109/cvpr42600.2020.00862
dc.identifier.urihttp://hdl.handle.net/10754/662461
dc.description.abstractWe present a novel learning-based approach for computing correspondences between non-rigid 3D shapes. Unlike previous methods that either require extensive training data or operate on handcrafted input descriptors and thus generalize poorly across diverse datasets, our approach is both accurate and robust to changes in shape structure. Key to our method is a feature-extraction network that learns directly from raw shape geometry, combined with a novel regularized map extraction layer and loss, based on the functional map representation. We demonstrate through extensive experiments in challenging shape matching scenarios that our method can learn from less training data than existing supervised approaches and generalizes significantly better than current descriptor-based learning methods. Our source code is available at: https://github.com/LIX-shape-analysis/GeomFmaps.
dc.description.sponsorshipThis work was supported by KAUST OSR Award No. CRG-2017-3426, a gift from Nvidia and the ERC Starting Grant No. 758800 (EXPROTEA).
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9156832/
dc.rightsArchived with thanks to IEEE
dc.titleDeep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence
dc.typeConference Paper
dc.conference.date13-19 June 2020
dc.conference.locationSeattle, WA, USA, USA
dc.eprint.versionPost-print
dc.contributor.institutionLIX, Ecole Polytechnique
dc.identifier.arxivid2003.14286
kaust.grant.numberCRG-2017-3426
refterms.dateFOA2020-04-09T07:19:55Z
kaust.acknowledged.supportUnitOSR
dc.date.published-online2020-08-05
dc.date.published-print2020-06
dc.date.posted2020-03-31


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
6.116Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record