用图注意力网络修复激光雷达缺失的垂直波束，仅靠单帧点云就能恢复精度达10厘米。
A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams
- 将点云建模为带顺序信息的图结构，用多层图注意力学习局部几何特征。
- 在KITTI数据上平均高度误差11.67厘米，87.98%点重建误差小于10厘米。
- 无需相机或时序信息，适合车载实时系统，对邻域大小鲁棒。
旋转式激光雷达因硬件老化、灰尘、雪、雾或强反射导致垂直波束丢失，使点云缺失整列垂直数据，严重损害自动驾驶的三维感知。本文提出一种基于图注意力网络（GAT）的框架，仅使用当前激光雷达帧即可重建缺失的垂直通道，不依赖相机图像或时间序列信息。将每帧激光雷达扫描表示为无序空间图：点为节点，邻近点间连边并保留原始波束索引顺序。多层GAT在局部几何邻域内学习自适应注意力权重，并直接回归缺失位置的高程（z）值。在1,065段模拟通道丢失的KITTI原始序列上训练与评估，方法平均高度均方根误差为11.67厘米，87.98%的重建点误差在10厘米以内。单张帧推理耗时14.65秒（单个GPU），且重建质量对邻域大小k保持稳定。结果表明，仅基于原始点云几何的纯图注意力模型可在真实传感器退化条件下有效恢复缺失垂直波束。
原文摘要 · Abstract (English)
Vertical beam dropout in spinning LiDAR sensors triggered by hardware aging, dust, snow, fog, or bright reflections removes entire vertical slices from the point cloud and severely degrades 3D perception in autonomous vehicles. This paper proposes a Graph Attention Network (GAT)-based framework that reconstructs these missing vertical channels using only the current LiDAR frame, with no camera images or temporal information required. Each LiDAR sweep is represented as an unstructured spatial graph: points are nodes and edges connect nearby points while preserving the original beam-index ordering. A multi-layer GAT learns adaptive attention weights over local geometric neighborhoods and directly regresses the missing elevation (z) values at dropout locations. Trained and evaluated on 1,065 raw KITTI sequences with simulated channel dropout, the method achieves an average height RMSE of 11.67 cm, with 87.98% of reconstructed points falling within a 10 cm error threshold. Inference takes 14.65 seconds per frame on a single GPU, and reconstruction quality remains stable for different neighborhood sizes k. These results show that a pure graph attention model operating solely on raw point-cloud geometry can effectively recover dropped vertical beams under realistic sensor degradation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。