Point-LN:非パラメトリック位置エンコーディングを用いた効率的な点群分類のための軽量フレームワーク
Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding
FPSやk-NN、学習不要の位置エンコーディングといった非パラメトリック要素と軽量な学習可能分類器を組み合わせ、低計算コストで高精度な3D点群分類を実現するフレームワークを提案した。
著者: Marzieh Mohammadi, Amir Salarpour, Pedram MohajerAnsari
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
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.
