论文标题
深壳：无监督的形状对应关系，最佳运输
Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
论文作者
论文摘要
我们提出了一种针对3D形状对应的新型无监督学习方法，该方法将多尺度匹配管道构建为深神经网络。这种方法基于光滑的壳，即当前最新的公理通信方法，该方法需要在初始姿势的空间上进行先验的随机搜索。我们的目标是通过直接从输入表面学习良好的初始化来替换这个昂贵的预处理步骤。为此，我们从熵正规化的最佳传输中系统地得出了完全可区分的，分层的匹配管道。这使我们可以将其与基于光滑，截断的光谱卷积过滤器的本地特征提取器结合。最后，我们表明，即使与最新的监督方法相比，即使是在多个数据集上，提出的无监督方法都显着改善了多个数据集的最新方法。此外，我们通过将学习过滤器应用于显着偏离训练集的示例来证明令人信服的概括结果。
We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network. This approach is based on smooth shells, the current state-of-the-art axiomatic correspondence method, which requires an a priori stochastic search over the space of initial poses. Our goal is to replace this costly preprocessing step by directly learning good initializations from the input surfaces. To that end, we systematically derive a fully differentiable, hierarchical matching pipeline from entropy regularized optimal transport. This allows us to combine it with a local feature extractor based on smooth, truncated spectral convolution filters. Finally, we show that the proposed unsupervised method significantly improves over the state-of-the-art on multiple datasets, even in comparison to the most recent supervised methods. Moreover, we demonstrate compelling generalization results by applying our learned filters to examples that significantly deviate from the training set.
