Papers › DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

16 Nov 2021arXiv:2111.08799archive 2025-07-28

Ruben Wiersma, Ahmad Nasikun, Elmar Eisemann, Klaus Hildebrandt

Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data. In this paper, we aim to construct anisotropic convolution layers that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce DeltaConv, a convolution layer that combines geometric operators from vector calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and match or improve on state-of-the-art approaches on several benchmarks, while also speeding up training and inference.

PaperPDFCode

Code

rubenwiersma/deltaconv officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Part Segmentation3D Point Cloud ClassificationClassificationDeep LearningPoint Cloud ClassificationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part DeltaConv (U-ResNet) Instance Average IoU 86.9 #10 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part DeltaNet Instance Average IoU 86.6 #20 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DeltaConv Mean class accuracy 91.2 #42 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DeltaConv Overall Accuracy 93.8 #42 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN DeltaConv Overall Accuracy 84.7 #57 of 77 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: DeltaConv

ConvolutionDeltaConv

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