3D Shape Registration Using Spectral Graph Embedding and Probabilistic Matching

06/21/2021
by   Avinash Sharma, et al.
0

We address the problem of 3D shape registration and we propose a novel technique based on spectral graph theory and probabilistic matching. The task of 3D shape analysis involves tracking, recognition, registration, etc. Analyzing 3D data in a single framework is still a challenging task considering the large variability of the data gathered with different acquisition devices. 3D shape registration is one such challenging shape analysis task. The main contribution of this chapter is to extend the spectral graph matching methods to very large graphs by combining spectral graph matching with Laplacian embedding. Since the embedded representation of a graph is obtained by dimensionality reduction we claim that the existing spectral-based methods are not easily applicable. We discuss solutions for the exact and inexact graph isomorphism problems and recall the main spectral properties of the combinatorial graph Laplacian; We provide a novel analysis of the commute-time embedding that allows us to interpret the latter in terms of the PCA of a graph, and to select the appropriate dimension of the associated embedded metric space; We derive a unit hyper-sphere normalization for the commute-time embedding that allows us to register two shapes with different samplings; We propose a novel method to find the eigenvalue-eigenvector ordering and the eigenvector signs using the eigensignature (histogram) which is invariant to the isometric shape deformations and fits well in the spectral graph matching framework, and we present a probabilistic shape matching formulation using an expectation maximization point registration algorithm which alternates between aligning the eigenbases and finding a vertex-to-vertex assignment.

READ FULL TEXT

page 12

page 21

page 22

research
12/14/2020

Articulated Shape Matching Using Laplacian Eigenfunctions and Unsupervised Point Registration

Matching articulated shapes represented by voxel-sets reduces to maximal...
research
08/14/2023

Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysis

This paper focuses on the statistical analysis of shapes of data objects...
research
11/26/2019

Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching

Graph matching involves combinatorial optimization based on edge-to-edge...
research
10/17/2017

Deep Spectral Descriptors: Learning the point-wise correspondence metric via Siamese deep neural networks

A robust and informative local shape descriptor plays an important role ...
research
07/18/2017

Spectral Filter Tracking

Visual object tracking is a challenging computer vision task with numero...
research
05/22/2023

RSA-INR: Riemannian Shape Autoencoding via 4D Implicit Neural Representations

Shape encoding and shape analysis are valuable tools for comparing shape...
research
12/02/2016

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

In this paper, we study the problem of semantic annotation on 3D models ...

Please sign up or login with your details

Forgot password? Click here to reset