DeltaConv

2000년 도입 · 논문 1편에서 사용

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.

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

소개 논문: DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds