SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization
This addresses the problem of non-rigid shape matching for computer vision and graphics applications, with incremental improvements over existing methods.
The paper tackled the challenge of establishing accurate point-to-point correspondences between non-rigid 3D shapes under non-isometric deformations and topological noise, resulting in SGMatch achieving competitive performance in near-isometric settings and consistent improvements in non-isometric scenarios.
Establishing accurate point-to-point correspondences between non-rigid 3D shapes remains a critical challenge, particularly under non-isometric deformations and topological noise. Existing functional map pipelines suffer from ambiguities that geometric descriptors alone cannot resolve, and spatial inconsistencies inherent in the projection of truncated spectral bases to dense pointwise correspondences. In this paper, we introduce SGMatch, a learning-based framework for semantic-guided non-rigid shape matching. Specifically, we design a Semantic-Guided Local Cross-Attention module that integrates semantic features from vision foundation models into geometric descriptors while preserving local structural continuity. Furthermore, we introduce a regularization objective based on conditional flow matching, which supervises a time-varying velocity field to encourage spatial smoothness of the recovered correspondences. Experimental results on multiple benchmarks demonstrate that SGMatch achieves competitive performance across near-isometric settings and consistent improvements under non-isometric deformations and topological noise.