DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Tianwei, Ma, Yong, Mei, Xiaoguang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917075069435904
author Ye, Tianwei
Ma, Yong
Mei, Xiaoguang
author_facet Ye, Tianwei
Ma, Yong
Mei, Xiaoguang
contents Establishing point-to-point correspondences across multiple 3D shapes is a fundamental problem in computer vision and graphics. In this paper, we introduce DcMatch, a novel unsupervised learning framework for non-rigid multi-shape matching. Unlike existing methods that learn a canonical embedding from a single shape, our approach leverages a shape graph attention network to capture the underlying manifold structure of the entire shape collection. This enables the construction of a more expressive and robust shared latent space, leading to more consistent shape-to-universe correspondences via a universe predictor. Simultaneously, we represent these correspondences in both the spatial and spectral domains and enforce their alignment in the shared universe space through a novel cycle consistency loss. This dual-level consistency fosters more accurate and coherent mappings. Extensive experiments on several challenging benchmarks demonstrate that our method consistently outperforms previous state-of-the-art approaches across diverse multi-shape matching scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01204
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency
Ye, Tianwei
Ma, Yong
Mei, Xiaoguang
Computer Vision and Pattern Recognition
Establishing point-to-point correspondences across multiple 3D shapes is a fundamental problem in computer vision and graphics. In this paper, we introduce DcMatch, a novel unsupervised learning framework for non-rigid multi-shape matching. Unlike existing methods that learn a canonical embedding from a single shape, our approach leverages a shape graph attention network to capture the underlying manifold structure of the entire shape collection. This enables the construction of a more expressive and robust shared latent space, leading to more consistent shape-to-universe correspondences via a universe predictor. Simultaneously, we represent these correspondences in both the spatial and spectral domains and enforce their alignment in the shared universe space through a novel cycle consistency loss. This dual-level consistency fosters more accurate and coherent mappings. Extensive experiments on several challenging benchmarks demonstrate that our method consistently outperforms previous state-of-the-art approaches across diverse multi-shape matching scenarios.
title DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.01204