用语义引导和流正则化提升非刚性3D形状匹配精度
SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization
- 融合视觉大模型语义特征与几何描述符，保持局部结构连续
- 通过时序条件流匹配实现点级特征传输，提升空间一致性
- 在非等距变形和拓扑噪声下仍表现稳健，适合复杂形变场景
在非等距变形和拓扑噪声下，建立非刚性3D形状间的精确点对点对应关系仍是关键挑战。现有功能映射方法因几何描述符无法解决歧义性，且截断谱基投影至稠密点对应时存在空间不一致问题。本文提出SGMatch，一种基于学习的框架，将3D提升的语义线索与轨迹级特征传输正则化相结合。具体地，设计了语义引导的局部交叉注意力模块，将视觉基础模型的语义特征融入几何描述符，同时保持局部结构连续性；进一步采用条件流匹配作为时间条件特征传输正则器，促进空间一致的点级恢复。在多个基准测试上的实验结果表明，SGMatch在近等距设置下达到竞争性性能，并在非等距变形和拓扑噪声下持续提升。
原文摘要 · Abstract (English)
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 that couples 3D-lifted semantic cues with trajectory-level feature transport regularization. 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 adapt conditional flow matching as a time-conditioned feature transport regularizer that promotes spatially coherent point-wise recovery. 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。