DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
In Person
Registration Categories
Full Conference Supporter
Full Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
This session WILL NOT be recorded.
TimeWednesday, 10 August 20229:05am - 9:13am PDT
LocationEast Building, Room 1-3
DescriptionAnisotropic convolution is a central building block of CNNs but challenging to transfer to surfaces. DeltaConv learns combinations and compositions of operators from vector calculus, which are a natural fit for curved surfaces. The result is a simple and robust anisotropic convolution operator for point clouds with state-of-the-art results.