Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding

2025/01/24 by Mohammadi, Marzieh, Salarpour, Amir, MohajerAnsari, Pedram · 1 citation
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2501.14238

Abstract

We introduce Point-LN, a novel lightweight framework engineered for efficient 3D point cloud classification. Point-LN integrates essential non-parametric components-such as Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and non-learnable positional encoding-with a streamlined learnable classifier that significantly enhances classification accuracy while maintaining a minimal parameter footprint. This hybrid architecture ensures low computational costs and rapid inference speeds, making Point-LN ideal for real-time and resource-constrained applications. Comprehensive evaluations on benchmark datasets, including ModelNet40 and ScanObjectNN, demonstrate that Point-LN achieves competitive performance compared to state-of-the-art methods, all while offering exceptional efficiency. These results establish Point-LN as a robust and scalable solution for diverse point cloud classification tasks, highlighting its potential for widespread adoption in various computer vision applications.

Cited by

• Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet

Related

• Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
• Learned Point Cloud Compression for Classification
• Revisiting Point Cloud Classification: A New Benchmark Dataset and\n Classification Model on Real-World Data
• PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification
• Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis