Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding
Year: 2025
Type: conference-paper
Abstract: We introduce Point-LN, a novel lightweight frame-work 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. For more details, see the code at: https://github.com/asalarpour/Point_LN.
Institutions: Sirjan University of Technology, Clemson University
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4409759731