Deformable Voxel Grids for Shape Comparisons - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

Deformable Voxel Grids for Shape Comparisons

Résumé

We 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.
Fichier principal
Vignette du fichier
paper-158-final-icdip-2022.pdf (11.55 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03863370 , version 1 (21-11-2022)

Identifiants

  • HAL Id : hal-03863370 , version 1

Citer

Raphaël Groscot, Laurent D. Cohen. Deformable Voxel Grids for Shape Comparisons. 14th International Conference on Digital Image Processing (ICDIP 2022), May 2022, Wuhan (Virtual), China. ⟨hal-03863370⟩
38 Consultations
28 Téléchargements

Partager

More