Unsupervised cycle-consistent deformation for shape matching

Abstract : We propose a self-supervised approach to deep surface deformation. Given a pair of shapes, our algorithm directly predicts a parametric transformation from one shape to the other respecting correspondences. Our insight is to use cycle-consistency to define a notion of good correspondences in groups of objects and use it as a supervisory signal to train our network. Our method does not rely on a template, assume near isometric deformations or rely on point-correspondence supervision. We demonstrate the efficacy of our approach by using it to transfer segmentation across shapes. We show, on Shapenet, that our approach is competitive with comparable state-of-the-art methods when annotated training data is readily available, but outperforms them by a large margin in the few-shot segmentation scenario.
Type de document :
Article dans une revue
Liste complète des métadonnées

https://hal-enpc.archives-ouvertes.fr/hal-02178969
Contributeur : Thibault Groueix <>
Soumis le : mercredi 10 juillet 2019 - 12:16:42
Dernière modification le : jeudi 11 juillet 2019 - 01:32:17

Lien texte intégral

Identifiants

  • HAL Id : hal-02178969, version 1
  • ARXIV : 1907.03165

Collections

Citation

Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry. Unsupervised cycle-consistent deformation for shape matching. Computer Graphics Forum, Wiley, 2019. ⟨hal-02178969⟩

Partager

Métriques

Consultations de la notice

24