Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence
Type
Conference PaperKAUST Grant Number
CRG-2017-3426Date
2020-08-05Preprint Posting Date
2020-03-31Online Publication Date
2020-08-05Print Publication Date
2020-06Permanent link to this record
http://hdl.handle.net/10754/662461
Metadata
Show full item recordAbstract
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 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.Citation
Donati, 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/cvpr42600.2020.00862Sponsors
This work was supported by KAUST OSR Award No. CRG-2017-3426, a gift from Nvidia and the ERC Starting Grant No. 758800 (EXPROTEA).ISBN
9781728171685arXiv
2003.14286Additional Links
https://ieeexplore.ieee.org/document/9156832/ae974a485f413a2113503eed53cd6c53
10.1109/cvpr42600.2020.00862