# Shape Classification using Spectral Graph Wavelets

## TL;DR

This paper introduces a spectral graph wavelet-based method for 3D shape classification, capturing local and global geometry through a three-step feature extraction process and demonstrating superior performance on benchmark datasets.

## Contribution

It presents a novel spectral graph wavelet approach combined with a bag-of-features framework for improved 3D shape classification.

## Key findings

- Effective shape classification on benchmark datasets
- Outperforms state-of-the-art methods
- Captures both local and global geometric features

## Abstract

Spectral shape descriptors have been used extensively in a broad spectrum of geometry processing applications ranging from shape retrieval and segmentation to classification. In this pa- per, we propose a spectral graph wavelet approach for 3D shape classification using the bag-of-features paradigm. In an effort to capture both the local and global geometry of a 3D shape, we present a three-step feature description framework. First, local descriptors are extracted via the spectral graph wavelet transform having the Mexican hat wavelet as a generating ker- nel. Second, mid-level features are obtained by embedding lo- cal descriptors into the visual vocabulary space using the soft- assignment coding step of the bag-of-features model. Third, a global descriptor is constructed by aggregating mid-level fea- tures weighted by a geodesic exponential kernel, resulting in a matrix representation that describes the frequency of appearance of nearby codewords in the vocabulary. Experimental results on two standard 3D shape benchmarks demonstrate the effective- ness of the proposed classification approach in comparison with state-of-the-art methods.