• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - Request a copy

Shape part Transfer via semantic latent space factorization

Groscot, Raphaël; Cohen, Laurent D.; Guibas, Leonidas (2019), Shape part Transfer via semantic latent space factorization, Geometric Science of Information 4th International Conference, GSI 2019, Toulouse, France, August 27–29, 2019, Proceedings, Springer : Berlin Heidelberg, p. 511-519. 10.1007/978-3-030-26980-7_53

Type
Communication / Conférence
Date
2019
Conference country
FRANCE
Book title
Geometric Science of Information 4th International Conference, GSI 2019, Toulouse, France, August 27–29, 2019, Proceedings; Proc. 4th conference on Geometric Science of Information (GSI2019)
Publisher
Springer
Published in
Berlin Heidelberg
ISBN
Print ISBN 978-3-030-26979-1
Pages
511-519
Publication identifier
10.1007/978-3-030-26980-7_53
Metadata
Show full item record
Author(s)
Groscot, Raphaël
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Cohen, Laurent D.
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Guibas, Leonidas
Abstract (EN)
We present a latent space factorization that controls a generative neural network for shapes in a semantic way. Our method uses the segmentation data present in a collection of shapes to explicitly factorize the encoder of a pointcloud autoencoder network, replacing it by several sub-encoders. This allows to learn a semantically-structured latent space in which we can uncover statistical modes corresponding to semantically similar shapes, as well as mixing parts from several objects to create hybrids and quickly explore design ideas through varying shape combinations. Our work differs from existing methods in two ways: first, it proves the usefulness of neural networks to achieve shape combinations and second, adapts the whole geometry of the object to accommodate for its different parts.
Subjects / Keywords
Autoencoder; Pointcloud; Latent space

Related items

Showing items related by title and author.

  • Thumbnail
    Volumetric Meshes: a Neural Network-friendly representation for 3D shapes generative models 
    Groscot, Raphaël; Bruna, Joan; Cohen, Laurent D. (2019) Communication / Conférence
  • Thumbnail
    Deformable voxel grids for shape comparisons 
    Groscot, Raphaël; Cohen, Laurent D. (2022) Communication / Conférence
  • Thumbnail
    Separable 3D Shape Representations for Shape Processing 
    Groscot, Raphaël (2021-06-29) Thèse
  • Thumbnail
    Incorporating Shape Variability in Image Segmentation via Implicit Template Deformation 
    Ardon, Roberto; Cohen, Laurent D.; Cuingnet, Rémi; Mory, Benoît; Prevost, Raphaël (2013) Communication / Conférence
  • Thumbnail
    Local vs global descriptors of hippocampus shape evolution for Alzheimer's longitudinal population analysis 
    Fiot, Jean-Baptiste; Risser, Laurent; Cohen, Laurent D.; Fripp, Jürgen; Vialard, François-Xavier (2012) Communication / Conférence
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo