Abstract
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: this https URL.
Abstract (translated)
本文介绍了GridNet-HD，这是一个用于三维语义分割的多模态数据集，专注于空中电力基础设施，并配对了高密度激光雷达与高分辨率倾斜影像。该数据集包含7,694张图像和25亿个点，被标记为11类，并且具有预定义的数据划分和mIoU度量标准。此外，还提供了单模态（仅激光雷达、仅图像）和多模态融合的基准模型。在GridNet-HD数据集上，融合模型相较于最佳单模态基线提高了+5.55 mIoU，这突显了几何信息与外观特征之间的互补性。根据第2节的回顾，目前没有公开的数据集同时提供高密度激光雷达和高分辨率倾斜影像以及针对电力线路资产的三维语义标签。数据集、基准模型和代码均可在以下网址获取：[此URL]。
URL
https://arxiv.org/abs/2601.13052
