Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence
KAUST Grant NumberCRG-2017-3426
Preprint Posting Date2020-03-31
Online Publication Date2020-08-05
Print Publication Date2020-06
Permanent link to this recordhttp://hdl.handle.net/10754/662461
MetadataShow full item record
AbstractWe 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 regularized 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: https://github.com/LIX-shape-analysis/GeomFmaps.
CitationDonati, N., Sharma, A., & Ovsjanikov, M. (2020). Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00862
SponsorsThis work was supported by KAUST OSR Award No. CRG-2017-3426, a gift from Nvidia and the ERC Starting Grant No. 758800 (EXPROTEA).