论文标题
使用热核无监督的致密形状对应
Unsupervised Dense Shape Correspondence using Heat Kernels
论文作者
论文摘要
在这项工作中，我们提出了一种无监督的方法，用于使用最近的深度功能地图框架来学习形状之间的密集对应关系。我们使用热核，而不是依赖于地面真相的对应关系或计算昂贵的测量距离。这些可以在培训期间快速计算为主管信号。此外，我们提出了使用不同的热扩散时间的课程学习策略，该策略在优化过程中提供了不同水平的难度，而无需采样机制或硬采矿。我们在不同的基准测试基准上介绍了我们的方法的结果，这些基准有各种挑战，例如部分性，拓扑噪声和不同的连接性。
In this work, we propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework. Instead of depending on ground-truth correspondences or the computationally expensive geodesic distances, we use heat kernels. These can be computed quickly during training as the supervisor signal. Moreover, we propose a curriculum learning strategy using different heat diffusion times which provide different levels of difficulty during optimization without any sampling mechanism or hard example mining. We present the results of our method on different benchmarks which have various challenges like partiality, topological noise and different connectivity.
