Show simple item record

dc.contributor.authorRakotosaona, Marie Julie
dc.contributor.authorOvsjanikov, Maks
dc.date.accessioned2021-06-29T12:56:57Z
dc.date.available2021-06-29T12:56:57Z
dc.date.issued2020-11-03
dc.identifier.citationRakotosaona, M.-J., & Ovsjanikov, M. (2020). Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation. Lecture Notes in Computer Science, 655–672. doi:10.1007/978-3-030-58536-5_39
dc.identifier.isbn9783030585358
dc.identifier.issn1611-3349
dc.identifier.issn0302-9743
dc.identifier.doi10.1007/978-3-030-58536-5_39
dc.identifier.urihttp://hdl.handle.net/10754/669821
dc.description.abstractWe present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines. Both the code and our pre-trained network can be found online: https://github.com/mrakotosaon/intrinsic_interpolations.
dc.description.sponsorshipParts of this work were supported by the KAUST CRG-2017-3426 Award and the ERC Starting Grant No. 758800 (EXPROTEA).
dc.publisherSpringer International Publishing
dc.relation.urlhttps://link.springer.com/10.1007/978-3-030-58536-5_39
dc.rightsArchived with thanks to Springer International Publishing
dc.titleIntrinsic Point Cloud Interpolation via Dual Latent Space Navigation
dc.typeConference Paper
dc.conference.date2020-08-23 to 2020-08-28
dc.conference.name16th European Conference on Computer Vision, ECCV 2020
dc.conference.locationGlasgow, GBR
dc.eprint.versionPost-print
dc.contributor.institutionLIX, Ecole Polytechnique, IP Paris, Palaiseau, France
dc.identifier.volume12347 LNCS
dc.identifier.pages655-672
dc.identifier.arxivid2004.01661
kaust.grant.numberCRG-2017-3426
dc.identifier.eid2-s2.0-85097222579
kaust.acknowledged.supportUnitCRG


This item appears in the following Collection(s)

Show simple item record