Groueix, ThibaultFisher, MatthewKim, Vladimir G.Russel, Bryan C.Aubry, MathieuBommes, David and Huang, Hui2019-07-112019-07-1120191467-8659https://doi.org/10.1111/cgf.13794https://diglib.eg.org:443/handle/10.1111/cgf13794We 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.10.1111/cgf.13794123-133