Unsupervised cycle-consistent deformation for shape matching


Thibault Groueix

Matthew Fisher

Vova Kim

Bryan Russell

Mathieu Aubry


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.





Pytorch implementation, data, and trained models for the project on https://github.com/ThibaultGROUEIX/CycleConsistentDeformation.


  title     = {Unsupervised cycle-consistent deformation for shape matching},
  author    = {Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu},
  booktitle = {Symposium on Geometry Processing (SGP)},
  year      = {2019}

Copyright Notice

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright.