用非线性神经函数映射提升不规则3D形状匹配精度
Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching
- 通过超网络生成非线性神经函数映射，替代传统线性方法
- 在部分、噪声点云等挑战场景下，匹配准确率显著提升
- 无需标注数据，可直接融入现有深度函数映射框架
函数映射是近年来非刚性3D形状匹配方法的核心，因其高效性和性能表现优异。然而，现有方法在部分形状、拓扑噪声和原始点云等挑战性场景中表现不佳。主要瓶颈在于显著的内在畸变导致截断谱基无法通过线性变换（即函数映射）准确对齐。为此，我们提出一种超网络，用于预测非线性神经函数映射（NFM），并以无监督方式学习该映射。具体地，将NFM建模为带跳跃连接的MLP，以优化标准函数映射，并使用超网络根据标准函数映射预测其权重。我们的框架采用新型无监督谱对齐损失进行训练。实验表明，该方法可无缝集成到当前最先进的无监督深度函数映射流程中，在高难度场景下显著提升匹配精度。
原文摘要 · Abstract (English)
Functional maps are the cornerstone of recent non-rigid 3D shape matching methods due to their efficiency and performance. However, existing methods struggle with challenging scenarios, such as partiality, topological noise, and raw point clouds. A primary bottleneck is that significant intrinsic distortion prevents truncated spectral bases from being accurately aligned via linear transformations (i.e., functional maps). To address this, we introduce a hyper-network that predicts non-linear neural functional maps (NFM), learned in an unsupervised manner, to better align spectral bases. Specifically, we model the NFM as an MLP with skip-connection to refine standard FM and employ a hyper-network to predict its weights, conditioned on standard FM. Our framework is trained using a novel unsupervised spectral alignment loss. Experiments demonstrate that our approach can be seamlessly integrated into state-of-the-art unsupervised deep functional map pipelines, substantially improving matching accuracy in demanding scenarios.
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。