Methods › Computer Vision › 3D Representations › DeltaConv
DeltaConv
Introduced by Ruben Wiersma et al. in DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds 16 Nov 2021 · 1 repository · arXiv:2111.08799
Tasks archive 2025-07-28
6 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| 3D Part Segmentation | 1 |
| 3D Point Cloud Classification | 1 |
| Classification | 1 |
| Deep Learning | 1 |
| Point Cloud Classification | 1 |
| Semantic Segmentation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections