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 CloudsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Part Segmentation | 1 | 20.00% |
3D Point Cloud Classification | 1 | 20.00% |
Classification | 1 | 20.00% |
Point Cloud Classification | 1 | 20.00% |
Semantic Segmentation | 1 | 20.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |