Coarse-to-Fine: A Hybrid Self-Supervised Method for Non-rigid 3D Shape Matching

2026-06-24

AI Summary

This work addresses the challenges of accuracy and robustness in non-rigid 3D shape matching under non-isometric deformations and topological noise by proposing a coarse-to-fine, self-supervised dual-branch framework. The method integrates Laplacian and elastic bases to construct a two-stream functional map, enabling joint learning of global coarse correspondences and local fine-grained alignment. A contrastive energy function is introduced to enhance feature discriminability, all without requiring manual annotations. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance across diverse complex scenarios while maintaining computational efficiency. Furthermore, the study validates the generalizability of the contrastive energy formulation as a plug-in enhancement for existing functional map-based methods.

Abstract

Non-rigid 3D shape matching is a fundamental task in computer vision and graphics. In this paper, we propose a hybrid self-supervised method based on a coarse-to-fine strategy, which ensures consistency between the coarse mapping and the refined correspondence produced by our refinement module. The architecture features a dual-branch design, consisting of two symmetric functional map learning streams: one based on the Laplacian basis and the other utilizing the elastic basis. Extensive experiments show that our approach not only maintains computational efficiency, but also achieves state-of-the-art performance across a variety of challenging scenarios, including non-isometric deformations and topological noise. Finally, we rigorously demonstrate that contrastive energies promote feature discrimination. Furthermore, integrating these energies with existing methods yields consistent improvements, validating the overall efficacy of our approach. Our code is available at https://github.com/LuoFeifan77/Coarse-to-Fine-Hybrid-Self-Supervised-Matching.

Problem

• non-rigid 3D shape matching
• functional map
• self-supervised learning
• coarse-to-fine
• shape correspondence

Innovation

• coarse-to-fine
• self-supervised
• functional map
• non-rigid 3D shape matching
• contrastive energy