Shape part Transfer via semantic latent space factorization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Shape part Transfer via semantic latent space factorization

Raphaël Groscot
  • Fonction : Auteur
  • PersonId : 1007807
Leonidas Guibas
  • Fonction : Auteur

Résumé

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 shapes collection 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 exploring 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.
Fichier principal
Vignette du fichier
shape_part_transfer_paper.pdf (1.84 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02281621 , version 1 (16-12-2020)

Identifiants

Citer

Raphaël Groscot, Laurent D. Cohen, Leonidas Guibas. Shape part Transfer via semantic latent space factorization. Geometric Science of Information (GSI2019), Aug 2019, Toulouse, France. pp.511-519, ⟨10.1007/978-3-030-26980-7_53⟩. ⟨hal-02281621⟩
92 Consultations
168 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More