Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching

TL;DR

This paper introduces an unsupervised contrastive learning framework combined with a simplified functional map architecture to improve the efficiency and robustness of 3D shape matching, outperforming existing methods.

Contribution

It presents the first unsupervised contrastive learning approach for 3D shape matching, eliminating the need for costly functional map solvers and enhancing feature quality.

Findings

Achieves state-of-the-art accuracy on multiple benchmarks.

Significantly reduces computational costs compared to traditional methods.

Outperforms supervised techniques in challenging scenarios.

Abstract

Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they primarily focus on optimizing pointwise and functional maps either individually or jointly, rather than directly enhancing feature representations in the embedding space, which often results in inadequate feature quality and suboptimal matching performance. Furthermore, these approaches heavily rely on traditional functional map techniques, such as time-consuming functional map solvers, which incur substantial computational costs. In this work, we introduce, for the first time, a novel unsupervised contrastive learning-based approach for efficient and robust 3D shape matching. We begin by presenting an unsupervised contrastive learning framework that promotes feature learning by maximizing consistency within positive similarity pairs and minimizing it within negative similarity pairs, thereby improving both the consistency and discriminability of the learned features.We then design a significantly simplified functional map learning architecture that eliminates the need for computationally expensive functional map solvers and multiple auxiliary functional map losses, greatly enhancing computational efficiency. By integrating these two components into a unified two-branch pipeline, our method achieves state-of-the-art performance in both accuracy and efficiency. Extensive experiments demonstrate that our approach is not only computationally efficient but also outperforms current state-of-the-art methods across various challenging benchmarks, including near-isometric, non-isometric, and topologically inconsistent scenarios, even surpassing supervised techniques.