Unsupervised cycle‐consistent deformation for shape matching

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...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum 2019-08, Vol.38 (5), p.123-133
Main Authors: Groueix, Thibault, Fisher, Matthew, Kim, Vladimir G., Russell, Bryan C., Aubry, Mathieu
Format: Article
Language:English
Subjects:
Algorithms
Computer graphics
Computer Science
Computer Vision and Pattern Recognition
Deformation
Segmentation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 combines 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.
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.13794