3D Representations

Anisotropic 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.

Source: DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds


Paper Code Results Date Stars



Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign