· Contributors · Organizations · Search
DiffusionNet: Discretization Agnostic Learning on Surfaces
Research & Education
Full Conference Supporter
Exhibitor Additional Full Conference
Exhibitor Full Conference
This session WILL NOT be recorded.
LocationEast Building, Room 1-3
DescriptionDiffusionNet is a general-purpose method for deep learning on meshes, points clouds, etc., via simple spatial diffusion. The networks generalize by construction across different samplings, resolutions, and representations of shapes and scale to high-resolution inputs. Spatial support is automatically optimized as a continuous parameter.