Papers › Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud...

Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks

28 Mar 2021arXiv:2103.15226archive 2025-07-28

Siddharth Srivastava, Gaurav Sharma

We propose simple yet effective improvements in point representations and local neighborhood graph construction within the general framework of graph neural networks (GNNs) for 3D point cloud processing. As a first contribution, we propose to augment the vertex representations with important local geometric information of the points, followed by nonlinear projection using a MLP. As a second contribution, we propose to improve the graph construction for GNNs for 3D point clouds. The existing methods work with a k-nn based approach for constructing the local neighborhood graph. We argue that it might lead to reduction in coverage in case of dense sampling by sensors in some regions of the scene. The proposed methods aims to counter such problems and improve coverage in such cases. As the traditional GNNs were designed to work with general graphs, where vertices may have no geometric interpretations, we see both our proposals as augmenting the general graphs to incorporate the geometric nature of 3D point clouds. While being simple, we demonstrate with multiple challenging benchmarks, with relatively clean CAD models, as well as with real world noisy scans, that the proposed method achieves state of the art results on benchmarks for 3D classification (ModelNet40) , part segmentation (ShapeNet) and semantic segmentation (Stanford 3D Indoor Scenes Dataset). We also show that the proposed network achieves faster training convergence, i.e. ~40% less epochs for classification. The project details are available at https://siddharthsrivastava.github.io/publication/geomgcnn/

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

3D Classification 3D Instance Segmentation 3D Part Segmentation 3D Point Cloud Classification LIDAR Semantic Segmentation Semantic Segmentation graph construction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Part Segmentation	ShapeNet-Part	GeomGCNN	Instance Average IoU	89.1	#1 of 67	Archive leaderboard	report
LIDAR Semantic Segmentation	Paris-Lille-3D	GeomGCNN	mIOU	0.785	#3 of 9	Archive leaderboard	report
Semantic Segmentation	S3DIS Area5	GeomGCNN	mIoU	69.4	#34 of 61	Archive leaderboard	report
Semantic Segmentation	S3DIS Area5	GeomGCNN	oAcc	89.4	#34 of 61	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

k-NN

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