Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Lingfeng, Zhang, Yuchen, Li, Hongsheng, Fu, Haoxiang, Tang, Yingbo, Ye, Hangjun, Chen, Long, Liang, Xiaojun, Hao, Xiaoshuai, Ding, Wenbo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911270096076800
author Zhang, Lingfeng
Zhang, Yuchen
Li, Hongsheng
Fu, Haoxiang
Tang, Yingbo
Ye, Hangjun
Chen, Long
Liang, Xiaojun
Hao, Xiaoshuai
Ding, Wenbo
author_facet Zhang, Lingfeng
Zhang, Yuchen
Li, Hongsheng
Fu, Haoxiang
Tang, Yingbo
Ye, Hangjun
Chen, Long
Liang, Xiaojun
Hao, Xiaoshuai
Ding, Wenbo
contents Vision-Language Models (VLMs), leveraging their powerful visual perception and reasoning capabilities, have been widely applied in Unmanned Aerial Vehicle (UAV) tasks. However, the spatial intelligence capabilities of existing VLMs in UAV scenarios remain largely unexplored, raising concerns about their effectiveness in navigating and interpreting dynamic environments. To bridge this gap, we introduce SpatialSky-Bench, a comprehensive benchmark specifically designed to evaluate the spatial intelligence capabilities of VLMs in UAV navigation. Our benchmark comprises two categories-Environmental Perception and Scene Understanding-divided into 13 subcategories, including bounding boxes, color, distance, height, and landing safety analysis, among others. Extensive evaluations of various mainstream open-source and closed-source VLMs reveal unsatisfactory performance in complex UAV navigation scenarios, highlighting significant gaps in their spatial capabilities. To address this challenge, we developed the SpatialSky-Dataset, a comprehensive dataset containing 1M samples with diverse annotations across various scenarios. Leveraging this dataset, we introduce Sky-VLM, a specialized VLM designed for UAV spatial reasoning across multiple granularities and contexts. Extensive experimental results demonstrate that Sky-VLM achieves state-of-the-art performance across all benchmark tasks, paving the way for the development of VLMs suitable for UAV scenarios. The source code is available at https://github.com/linglingxiansen/SpatialSKy.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13269
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
Zhang, Lingfeng
Zhang, Yuchen
Li, Hongsheng
Fu, Haoxiang
Tang, Yingbo
Ye, Hangjun
Chen, Long
Liang, Xiaojun
Hao, Xiaoshuai
Ding, Wenbo
Computer Vision and Pattern Recognition
Vision-Language Models (VLMs), leveraging their powerful visual perception and reasoning capabilities, have been widely applied in Unmanned Aerial Vehicle (UAV) tasks. However, the spatial intelligence capabilities of existing VLMs in UAV scenarios remain largely unexplored, raising concerns about their effectiveness in navigating and interpreting dynamic environments. To bridge this gap, we introduce SpatialSky-Bench, a comprehensive benchmark specifically designed to evaluate the spatial intelligence capabilities of VLMs in UAV navigation. Our benchmark comprises two categories-Environmental Perception and Scene Understanding-divided into 13 subcategories, including bounding boxes, color, distance, height, and landing safety analysis, among others. Extensive evaluations of various mainstream open-source and closed-source VLMs reveal unsatisfactory performance in complex UAV navigation scenarios, highlighting significant gaps in their spatial capabilities. To address this challenge, we developed the SpatialSky-Dataset, a comprehensive dataset containing 1M samples with diverse annotations across various scenarios. Leveraging this dataset, we introduce Sky-VLM, a specialized VLM designed for UAV spatial reasoning across multiple granularities and contexts. Extensive experimental results demonstrate that Sky-VLM achieves state-of-the-art performance across all benchmark tasks, paving the way for the development of VLMs suitable for UAV scenarios. The source code is available at https://github.com/linglingxiansen/SpatialSKy.
title Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.13269