AI RESEARCH
SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition
arXiv CS.LG
•
ArXi:2603.07454v1 Announce Type: cross We present SLNet, a lightweight backbone for 3D point cloud recognition designed to achieve strong performance without the computational cost of many recent attention, graph, and deep MLP based models. The model is built on two simple ideas: NAPE (Nonparametric Adaptive Point Embedding), which captures spatial structure using a combination of Gaussian RBF and cosine bases with input adaptive bandwidth and blending, and GMU (Geometric Modulation Unit), a per channel affine modulator that adds only 2D learnable parameters.