Ask a Question

Prefer a chat interface with context about you and your work?

DiffusionNet: Discretization Agnostic Learning on Surfaces

DiffusionNet: Discretization Agnostic Learning on Surfaces

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 surfaceā€”a basic property that is crucial for practical applications. ā€¦