用自监督学习生成对网格变化鲁棒的3D表面特征
Neural Descriptors: Self-Supervised Learning of Robust Local Surface Descriptors Using Polynomial Patches
- 通过合成数据与神经网络学习采样不变特征
- 在FAUST、SCAPE等基准上提升对应性能
- 特别抗拓扑噪声和部分形状干扰，适合几何分析
传统形状描述子如热核签名（HKS）、波核签名（WKS）和方向直方图签名（SHOT）虽广泛用于形状分析，但对网格连接性、采样模式和拓扑噪声敏感。尽管微分几何理论提供理论上鲁棒的微分不变量，但在离散网格上计算这些不变量常导致数值不稳定，限制实际应用。本文提出一种自监督学习方法，从3D表面提取几何特征。结合合成数据生成与神经架构，学习采样不变特征。将所提特征融入现有形状对应框架，在标准基准如FAUST、SCAPE、TOPKIDS和SHREC'16上实现性能提升，尤其在面对拓扑噪声和部分形状时表现出强鲁棒性。
原文摘要 · Abstract (English)
Classical shape descriptors such as Heat Kernel Signature (HKS), Wave Kernel Signature (WKS), and Signature of Histograms of OrienTations (SHOT), while widely used in shape analysis, exhibit sensitivity to mesh connectivity, sampling patterns, and topological noise. While differential geometry offers a promising alternative through its theory of differential invariants, which are theoretically guaranteed to be robust shape descriptors, the computation of these invariants on discrete meshes often leads to unstable numerical approximations, limiting their practical utility. We present a self-supervised learning approach for extracting geometric features from 3D surfaces. Our method combines synthetic data generation with a neural architecture designed to learn sampling-invariant features. By integrating our features into existing shape correspondence frameworks, we demonstrate improved performance on standard benchmarks including FAUST, SCAPE, TOPKIDS, and SHREC'16, showing particular robustness to topological noise and partial shapes.
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。