Learning Canonical Embedding for Non-rigid Shape Matching

2021/10/06 by Abhishek Sharma, Maks Ovsjanikov, Sharma, Abhishek +1
Computer Science · Engineering · #3D Shape Modeling and Analysis #Artificial Intelligence (cs.AI) #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #Human Pose and Action Recognition #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2110.02994

openalex publication_date 2021/10/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Functional maps
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Matrix Decomposition on Graphs: A Functional View
• Continuous Surface Embeddings

Related

• Joint Symmetry Detection and Shape Matching for Non-Rigid Point Cloud
• Learning Canonical Embeddings for Unsupervised Shape Correspondence with Locally Linear Transformations
• Smoothness and effective regularizations in learned embeddings for shape matching
• Revisiting Map Relations for Unsupervised Non-Rigid Shape Matching
• Non-Rigid Shape Registration via Deep Functional Maps Prior