PointViG: A Lightweight GNN-based Model for Efficient Point Cloud Analysis

TL;DR

PointViG is a lightweight, efficient GNN-based model for point cloud analysis that balances high performance with low computational complexity, suitable for resource-constrained environments.

Contribution

The paper introduces PointViG, a novel GNN framework with a lightweight convolutional module and adaptive dilated graph convolution for scalable, efficient point cloud processing.

Findings

Achieves 94.3% accuracy on ModelNet40 with 1.5M parameters.

Attains 71.7% mIoU on S3DIS with 5.3M parameters.

Balances performance and efficiency effectively.

Abstract

In the domain of point cloud analysis, despite the significant capabilities of Graph Neural Networks (GNNs) in managing complex 3D datasets, existing approaches encounter challenges like high computational costs and scalability issues with extensive scenarios. These limitations restrict the practical deployment of GNNs, notably in resource-constrained environments. To address these issues, this study introduce <b>Point<\b> <b>Vi<\b>sion <b>G<\b>NN (PointViG), an efficient framework for point cloud analysis. PointViG incorporates a lightweight graph convolutional module to efficiently aggregate local features and mitigate over-smoothing. For large-scale point cloud scenes, we propose an adaptive dilated graph convolution technique that searches for sparse neighboring nodes within a dilated neighborhood based on semantic correlation, thereby expanding the receptive field and ensuring computational efficiency. Experiments demonstrate that PointViG achieves performance comparable to state-of-the-art models while balancing performance and complexity. On the ModelNet40 classification task, PointViG achieved 94.3% accuracy with 1.5M parameters. For the S3DIS segmentation task, it achieved an mIoU of 71.7% with 5.3M parameters. These results underscore the potential and efficiency of PointViG in point cloud analysis.