GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure
This addresses the lack of public datasets for power-line asset analysis, benefiting researchers in remote sensing and infrastructure monitoring, but it is incremental as it focuses on dataset creation and baseline evaluation.
The paper introduces GridNet-HD, a high-resolution multi-modal dataset for 3D semantic segmentation of power line infrastructure, combining LiDAR and imagery, and shows that fusion models achieve a +5.55 mIoU improvement over unimodal baselines.
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.