Deep shells: Unsupervised shape correspondence with optimal transport
Eisenberger M, Toker A, Leal-Taixé L, Cremers D (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: Neural information processing systems foundation
Book Volume: 2020-December
Conference Proceedings Title: Advances in Neural Information Processing Systems
Event location: Virtual, Online
Abstract
We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network. This approach is based on smooth shells, the current state-of-the-art axiomatic correspondence method, which requires an a priori stochastic search over the space of initial poses. Our goal is to replace this costly preprocessing step by directly learning good initializations from the input surfaces. To that end, we systematically derive a fully differentiable, hierarchical matching pipeline from entropy regularized optimal transport. This allows us to combine it with a local feature extractor based on smooth, truncated spectral convolution filters. Finally, we show that the proposed unsupervised method significantly improves over the state-of-the-art on multiple datasets, even in comparison to the most recent supervised methods. Moreover, we demonstrate compelling generalization results by applying our learned filters to examples that significantly deviate from the training set.
Involved external institutions
Germany (DE)How to cite
APA:
Eisenberger, M., Toker, A., Leal-Taixé, L., & Cremers, D. (2020). Deep shells: Unsupervised shape correspondence with optimal transport. In Advances in Neural Information Processing Systems. Virtual, Online: Neural information processing systems foundation.
MLA:
Eisenberger, Marvin, et al. "Deep shells: Unsupervised shape correspondence with optimal transport." Proceedings of the 34th Conference on Neural Information Processing Systems, NeurIPS 2020, Virtual, Online Neural information processing systems foundation, 2020.
BibTeX: Download