Show simple item record

dc.contributor.authorMarin, Riccardo
dc.contributor.authorRampini, Arianna
dc.contributor.authorCastellani, Umberto
dc.contributor.authorRodola, Emanuele
dc.contributor.authorOvsjanikov, Maks
dc.contributor.authorMelzi, Simone
dc.date.accessioned2021-08-18T11:58:14Z
dc.date.available2021-08-18T11:58:14Z
dc.date.issued2021-07-22
dc.identifier.citationMarin, R., Rampini, A., Castellani, U., Rodolà, E., Ovsjanikov, M., & Melzi, S. (2021). Spectral Shape Recovery and Analysis Via Data-driven Connections. International Journal of Computer Vision. doi:10.1007/s11263-021-01492-6
dc.identifier.issn1573-1405
dc.identifier.issn0920-5691
dc.identifier.doi10.1007/s11263-021-01492-6
dc.identifier.urihttp://hdl.handle.net/10754/670667
dc.description.abstractAbstractWe introduce a novel learning-based method to recover shapes from their Laplacian spectra, based on establishing and exploring connections in a learned latent space. The core of our approach consists in a cycle-consistent module that maps between a learned latent space and sequences of eigenvalues. This module provides an efficient and effective link between the shape geometry, encoded in a latent vector, and its Laplacian spectrum. Our proposed data-driven approach replaces the need for ad-hoc regularizers required by prior methods, while providing more accurate results at a fraction of the computational cost. Moreover, these latent space connections enable novel applications for both analyzing and controlling the spectral properties of deformable shapes, especially in the context of a shape collection. Our learning model and the associated analysis apply without modifications across different dimensions (2D and 3D shapes alike), representations (meshes, contours and point clouds), nature of the latent space (generated by an auto-encoder or a parametric model), as well as across different shape classes, and admits arbitrary resolution of the input spectrum without affecting complexity. The increased flexibility allows us to address notoriously difficult tasks in 3D vision and geometry processing within a unified framework, including shape generation from spectrum, latent space exploration and analysis, mesh super-resolution, shape exploration, style transfer, spectrum estimation for point clouds, segmentation transfer and non-rigid shape matching.
dc.description.sponsorshipWe gratefully acknowledge Luca Moschella and Silvia Casola for the technical support, Nicholas Sharp for the useful suggestions about pointcloud spectra. Parts of this work were supported by the KAUST OSR Award No. CRG-2017-3426, the ERC Starting Grant No. 758800 (EXPROTEA), the ERC Starting Grant No. 802554 (SPECGEO), the ANR AI Chair AIGRETTE, and the MIUR under grant “Dipartimenti di eccellenza 2018-2022” of the Department of Computer Science of Sapienza University and University of Verona.
dc.publisherSpringer Science and Business Media LLC
dc.relation.urlhttps://link.springer.com/10.1007/s11263-021-01492-6
dc.rightsArchived with thanks to INTERNATIONAL JOURNAL OF COMPUTER VISION
dc.rights.urihttps://creativecommons.org/licenses/by/4.0
dc.subjectShape from spectrum
dc.subjectSpectral geometry
dc.subjectShape analysis
dc.subjectRepresentation learning
dc.subjectGeometry processing
dc.titleSpectral Shape Recovery and Analysis Via Data-driven Connections
dc.typeArticle
dc.identifier.journalINTERNATIONAL JOURNAL OF COMPUTER VISION
dc.rights.embargodate2022-08-18
dc.identifier.wosutWOS:000678053000001
dc.eprint.versionPost-print
dc.contributor.institutionSapienza University of Rome, Rome, Italy
dc.contributor.institutionUniversity of Verona, Verona, Italy
dc.contributor.institutionLIX, Ecole Polytechnique, IP Paris, France
kaust.grant.numberCRG-2017-3426
kaust.grant.numberOSR
dc.identifier.eid2-s2.0-85111094513
kaust.acknowledged.supportUnitCRG
kaust.acknowledged.supportUnitOSR
dc.date.published-online2021-07-22
dc.date.published-print2021-10


This item appears in the following Collection(s)

Show simple item record

Archived with thanks to INTERNATIONAL JOURNAL OF COMPUTER VISION
Except where otherwise noted, this item's license is described as Archived with thanks to INTERNATIONAL JOURNAL OF COMPUTER VISION