Learning Canonical Embedding for Non-rigid Shape Matching

TL;DR

This paper introduces an end-to-end deep learning framework that learns canonical embeddings for non-rigid shape matching, outperforming existing methods on standard benchmarks with improved efficiency and robustness.

Contribution

The novel framework learns canonical embeddings end-to-end, avoiding traditional constraints and instabilities, and demonstrates superior performance on shape matching benchmarks.

Findings

Outperforms recent learning-based shape matching methods

Achieves higher accuracy on FAUST and SHREC datasets

Is computationally cheaper and more data-efficient

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.