Unsupervised Learning of Dense Shape Correspondence

Oshri Halimi, Or Litany, Emanuele Rodola, Alex M. Bronstein, Ron Kimmel; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4370-4379

Abstract


We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the understanding that natural deformations (such as changes in pose) approximately preserve the metric structure of the surface, yielding a natural criterion to drive the learning process toward distortion-minimizing predictions. On this basis, we overcome the need for annotated data and replace it by a purely geometric criterion. The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase. In contrast to existing supervised approaches which specialize on the class seen at training time, we demonstrate stronger generalization as well as applicability to a variety of challenging settings. We showcase our method on a wide selection of correspondence benchmarks, where we outperform other methods in terms of accuracy, generalization, and efficiency.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Halimi_2019_CVPR,
author = {Halimi, Oshri and Litany, Or and Rodola, Emanuele and Bronstein, Alex M. and Kimmel, Ron},
title = {Unsupervised Learning of Dense Shape Correspondence},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}