Skip to Main content Skip to Navigation
Conference papers

Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence

Abstract : We present a novel learning-based approach for computing correspondences between non-rigid 3D shapes. Unlike previous methods that either require extensive training data or operate on handcrafted input descriptors and thus generalize poorly across diverse datasets, our approach is both accurate and robust to changes in shape structure. Key to our method is a feature-extraction network that learns directly from raw shape geometry, combined with a novel reg-ularized map extraction layer and loss, based on the functional map representation. We demonstrate through extensive experiments in challenging shape matching scenarios that our method can learn from less training data than existing supervised approaches and generalizes significantly better than current descriptor-based learning methods. Our source code is available at: LIX-shape-analysis/GeomFmaps.
Complete list of metadata

Cited literature [53 references]  Display  Hide  Download
Contributor : Nicolas Donati Connect in order to contact the contributor
Submitted on : Thursday, November 12, 2020 - 11:09:26 AM
Last modification on : Saturday, November 21, 2020 - 3:29:55 AM
Long-term archiving on: : Saturday, February 13, 2021 - 7:03:59 PM


Files produced by the author(s)


  • HAL Id : hal-03001057, version 1



Nicolas Donati, Abhishek Sharma, Maks Ovsjanikov. Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence. CVPR, Jun 2020, Seattle (virtual), United States. ⟨hal-03001057⟩



Record views


Files downloads