DiffusionNet: Discretization Agnostic Learning on Surfaces
DiffusionNet: Discretization Agnostic Learning on Surfaces
复制标题
DOI：
10.1145/3507905
复制
发表时间：
2022-03-01
影响因子：
6.2
通讯作者：
Ovsjanikov, Maks
中科院分区：
文献类型：
--
作者：
Sharp, Nicholas;Attaiki, Souhaib;Ovsjanikov, Maks
我们引入了一种新的通用方法来进行三维表面上的深度学习，这是基于简单的扩散层对于空间通信非常有效的见解。由此产生的网络自动鲁棒的分辨率和采样的表面的变化，一个基本的属性，是至关重要的实际应用。我们的网络可以在各种几何表示上离散化，例如三角形网格或点云，甚至可以在一种表示上训练，然后应用于另一种表示。我们优化扩散的空间支持作为一个连续的网络参数，范围从纯粹的本地到完全全球，消除手动选择邻域大小的负担。该方法中唯一的其他成分是在每个点上独立应用的多层感知器和支持方向滤波器的空间梯度特征。由此产生的网络是简单的，强大的，高效的。在这里，我们主要关注三角形网格表面，并展示了各种任务的最先进的结果，包括表面分类，分割和非刚性对应。
We introduce a new general-purpose approach to deep learning on three-dimensional surfaces based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in resolution and sampling of a surface-a basic property that is crucial for practical applications. Our networks can be discretized on various geometric representations, such as triangle meshes or point clouds, and can even be trained on one representation and then applied to another. We optimize the spatial support of diffusion as a continuous network parameter ranging from purely local to totally global, removing the burden of manually choosing neighborhood sizes. The only other ingredients in the method are a multi-layer perceptron applied independently at each point and spatial gradient features to support directional filters. The resulting networks are simple, robust, and efficient. Here, we focus primarily on triangle mesh surfaces and demonstrate state-of-the-art results for a variety of tasks, including surface classification, segmentation, and non-rigid correspondence.