Show simple item record

Deformable voxel grids for shape comparisons

hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorGroscot, Raphaël
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorCohen, Laurent D.
dc.date.accessioned2023-02-13T13:50:26Z
dc.date.available2023-02-13T13:50:26Z
dc.date.issued2022
dc.identifier.urihttps://basepub.dauphine.psl.eu/handle/123456789/24056
dc.language.isoenen
dc.subjectShape morphingen
dc.subjectdeformable modelsen
dc.subjectgenerative 3D modelingen
dc.subject.ddc4en
dc.titleDeformable voxel grids for shape comparisonsen
dc.typeCommunication / Conférence
dc.contributor.editoruniversitytrue
dc.description.abstractenWe present Deformable Voxel Grids (DVGs) for 3D shapes comparison and processing. It consists of a voxel grid which is deformed to approximate the silhouette of a shape, via energy-minimization. By interpreting the DVG as a local coordinates system, it provides a better embedding space than a regular voxel grid, since it is adapted to the geometry of the shape. It also allows to deform the shape by moving the control points of the DVG, in a similar manner to the Free Form Deformation, but with easier interpretability of the control points positions. After proposing a computation scheme of the energies compatible with meshes and pointclouds, we demonstrate the use of DVGs in a variety of applications: correspondences via cubification, style transfer, shape retrieval and PCA deformations. The first two require no learning and can be readily run on any shapes in a matter of minutes on modest hardware. As for the last two, they require to first optimize DVGs on a collection of shapes, which amounts to a pre-processing step. Then, determining PCA coordinates is straightforward and brings a few parameters to deform a shape.en
dc.relation.ispartoftitleFourteenth International Conference on Digital Image Processing (ICDIP 2022)en
dc.relation.ispartofeditorXudong Jiang, Wenbing Tao, Deze Zeng, Yi Xie
dc.relation.ispartofpublnameSPIEen
dc.relation.ispartofurl10.1117/12.2657766en
dc.subject.ddclabelInformatique généraleen
dc.relation.ispartofisbn9781510657564en
dc.relation.conftitleFourteenth International Conference on Digital Image Processing (ICDIP 2022)en
dc.relation.confdate2022-05
dc.relation.confcityWuhanen
dc.relation.confcountryChinaen
dc.relation.forthcomingnonen
dc.identifier.doi10.1117/12.2645961en
dc.description.ssrncandidatenon
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2023-02-13T13:46:08Z
hal.author.functionaut
hal.author.functionaut


Files in this item

Thumbnail
Name:
paper-158-final-icdip-2022.pdf
Size:
2.172Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record