高精度激光雷达与影像融合数据集，助力电力线路三维语义分割
GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure
- 融合高密度激光雷达与高清倾斜影像，构建电力线路多模态数据集
- 融合模型比最优单模态提升5.55点mIoU，验证几何与视觉互补性
- 适合电力巡检、三维重建与多模态学习研究者使用
本文提出GridNet-HD，一个用于架空电力设施三维语义分割的多模态数据集，结合高密度激光雷达点云与高分辨率倾斜影像。数据集包含7,694张图像和25亿个点，标注为11类，提供预定义划分及mIoU评估指标。同时提供了单模态（仅激光雷达、仅影像）与多模态融合基线。在GridNet-HD上，融合模型相较最佳单模态基线提升5.55 mIoU，凸显几何与外观信息的互补优势。据第2节综述，目前尚无公开数据集能同时提供高密度激光雷达、高分辨率倾斜影像及电力资产的3D语义标签。数据集、基线与代码已开源：https://huggingface.co/collections/heig-vd-geo/gridnet-hd。
原文摘要 · Abstract (English)
This paper presents GridNet-HD, a multi-modal dataset for 3D semantic segmentation of overhead electrical infrastructures, pairing high-density LiDAR with high-resolution oblique imagery. The dataset comprises 7,694 images and 2.5 billion points annotated into 11 classes, with predefined splits and mIoU metrics. Unimodal (LiDAR-only, image-only) and multi-modal fusion baselines are provided. On GridNet-HD, fusion models outperform the best unimodal baseline by +5.55 mIoU, highlighting the complementarity of geometry and appearance. As reviewed in Sec. 2, no public dataset jointly provides high-density LiDAR and high-resolution oblique imagery with 3D semantic labels for power-line assets. Dataset, baselines, and codes are available: https://huggingface.co/collections/heig-vd-geo/gridnet-hd.
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。