Invention Description Conducting learning-based models on large-scale unstructured geometric data, particularly volumetric 3D meshes, remains a significant challenge. While previous methods have employed graph convolutional approaches, they suffer from high space complexity, limiting efficient mini-batch training, as well as fixed short-range feature...

There has been much research into developing learning methods on non-Euclidean domains such as point clouds, various meshes and graphs. However, very few have studied CNNs on tetrahedral meshes, which are highly useful in medical imaging applications. Tetrahedral meshes have millions of edges and vertices and existing graph convolutional networks are...