Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Learning Canonical Embedding for Non-rigid Shape Matching

Abstract : This paper provides a novel framework that learns canonical embeddings for non-rigid shape matching. In contrast to prior work in this direction, our framework is trained end-to-end and thus avoids instabilities and constraints associated with the commonly-used Laplace-Beltrami basis or sequential optimization schemes. On multiple datasets, we demonstrate that learning self symmetry maps with a deep functional map projects 3D shapes into a low dimensional canonical embedding that facilitates non-rigid shape correspondence via a simple nearest neighbor search. Our framework outperforms multiple recent learning based methods on FAUST and SHREC benchmarks while being computationally cheaper, data efficient, and robust.
Complete list of metadata
Contributor : Abhishek Sharma Connect in order to contact the contributor
Submitted on : Wednesday, October 6, 2021 - 2:36:42 AM
Last modification on : Saturday, October 9, 2021 - 4:03:34 AM


Files produced by the author(s)


  • HAL Id : hal-03251317, version 2



Abhishek Sharma, Maks Ovsjanikov. Learning Canonical Embedding for Non-rigid Shape Matching. 2021. ⟨hal-03251317v2⟩



Record views


Files downloads