DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency
This addresses the fundamental problem of multi-shape matching in computer vision and graphics, offering a novel approach with broad applicability.
The paper tackled the problem of establishing point-to-point correspondences across multiple 3D shapes by introducing DcMatch, an unsupervised learning framework that leverages a shape graph attention network and dual-level consistency, resulting in consistent outperformance over previous state-of-the-art methods on challenging benchmarks.
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.