Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
This provides a solution for real-time, resource-constrained applications in 3D vision, such as robotics or augmented reality, by matching the performance of trained models without learnable parameters, though it is incremental in its approach.
The paper tackled efficient 3D point cloud classification by introducing Point-GN, a non-parametric network that uses Gaussian positional encoding and other non-learnable components, achieving accuracies of 85.29% on ModelNet40 and 85.89% on ScanObjectNN while reducing computational complexity.
This paper introduces Point-GN, a novel non-parametric network for efficient and accurate 3D point cloud classification. Unlike conventional deep learning models that rely on a large number of trainable parameters, Point-GN leverages non-learnable components-specifically, Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and Gaussian Positional Encoding (GPE)-to extract both local and global geometric features. This design eliminates the need for additional training while maintaining high performance, making Point-GN particularly suited for real-time, resource-constrained applications. We evaluate Point-GN on two benchmark datasets, ModelNet40 and ScanObjectNN, achieving classification accuracies of 85.29% and 85.89%, respectively, while significantly reducing computational complexity. Point-GN outperforms existing non-parametric methods and matches the performance of fully trained models, all with zero learnable parameters. Our results demonstrate that Point-GN is a promising solution for 3D point cloud classification in practical, real-time environments.