Unsupervised cycle-consistent deformation for shape matching
This work addresses shape matching for computer graphics and vision applications, offering a novel unsupervised method that reduces reliance on annotated data.
The paper tackles the problem of shape matching by proposing a self-supervised approach that uses cycle-consistency to predict parametric transformations between shapes without relying on templates or supervised correspondences. It demonstrates competitive performance with state-of-the-art methods on Shapenet in fully supervised settings and outperforms them significantly in few-shot segmentation scenarios.
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.