· Contributors · Organizations · Search
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
Research & Education
Full Conference Supporter
Virtual Conference Supporter
Exhibitor Additional Full Conference
Exhibitor Full Conference
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.