Unsupervised cycle-consistent deformation for shape matching - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Computer Graphics Forum Année : 2019

Unsupervised cycle-consistent deformation for shape matching

(1) , (2) , , (3) , (4)
Thibault Groueix
Vladimir G. Kim
  • Fonction : Auteur
Bryan C. Russell
  • Fonction : Auteur
  • PersonId : 964163
Mathieu Aubry
  • Fonction : Auteur
  • PersonId : 945627


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.

Dates et versions

hal-02178969 , version 1 (10-07-2019)



Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry. Unsupervised cycle-consistent deformation for shape matching. Computer Graphics Forum, 2019, 38 (5), pp.123-133. ⟨10.1111/cgf.13794⟩. ⟨hal-02178969⟩
74 Consultations
0 Téléchargements



Gmail Facebook Twitter LinkedIn More