Are VLMs Lost Between Sky and Space? LinkS$^2$Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence

• URL: http://arxiv.org/abs/2604.02020v1
• Date: Thu, 02 Apr 2026 13:22:57 GMT
• Title: Are VLMs Lost Between Sky and Space? LinkS$^2$Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence
• Abstract summary: LinkS$2$Bench links 1,022 minutes of dynamic UAV footage with high-resolution satellite imagery covering over 200 km$2$.<n>Through an LMM-assisted pipeline and rigorous human annotation, we constructed 17.9k high-quality question-answer pairs.<n> Evaluations reveal a substantial gap compared to human baselines, identifying accurate cross-view dynamic alignment as the critical bottleneck.
• Score: 107.79496500634691
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Synergistic spatial intelligence between UAVs and satellites is indispensable for emergency response and security operations, as it uniquely integrates macro-scale global coverage with dynamic, real-time local perception. However, the capacity of Vision-Language Models (VLMs) to master this complex interplay remains largely unexplored. This gap persists primarily because existing benchmarks are confined to isolated Unmanned Aerial Vehicle (UAV) videos or static satellite imagery, failing to evaluate the dynamic local-to-global spatial mapping essential for comprehensive cross-view reasoning. To bridge this gap, we introduce LinkS$^2$Bench, the first comprehensive benchmark designed to evaluate VLMs' wide-area, dynamic cross-view spatial intelligence. LinkS$^2$Bench links 1,022 minutes of dynamic UAV footage with high-resolution satellite imagery covering over 200 km$^2$. Through an LMM-assisted pipeline and rigorous human annotation, we constructed 17.9k high-quality question-answer pairs comprising 12 fine-grained tasks across four dimensions: perception, localization, relation, and reasoning. Evaluations of 18 representative VLMs reveal a substantial gap compared to human baselines, identifying accurate cross-view dynamic alignment as the critical bottleneck. To alleviate this, we design a Cross-View Alignment Adapter, demonstrating that explicit alignment significantly improves model performance. Furthermore, fine-tuning experiments underscore the potential of LinkS$^2$Bench in advancing VLM adaptation for complex spatial reasoning.

Related papers

• AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience [32.90229217189434]
  We propose SatAgent, a UAV-Satellite collaborative spatial reasoning model.<n>By leveraging satellite and UAV perspectives, SatAgent enables robust, accurate reasoning in complex urban environments.<n>We construct SatAgent-SR130K, the first large-scale UAV-Satellite collaborative multi-view spatial reasoning dataset.
  arXiv  Detail & Related papers  (2026-06-30T10:46:23Z)
• AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration [22.635145889984273]
  We present AirGroundBench, a diagnostic benchmark for evaluating multi-view spatial intelligence in UAV-UGV collaboration.<n>AirGroundBench is built from 11 high-fidelity simulated environments with 1,021 synchronized air-ground observation pairs.<n>It covers 10 task types organized into four progressively demanding capability dimensions.
  arXiv  Detail & Related papers  (2026-06-26T12:51:22Z)
• CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming [13.534076118011603]
  We introduce CVSBench, a large-scale benchmark for evaluating cross-view spatial reasoning through satellite-street pairs.<n>This benchmark supports multiple tasks, including cross-view VQA, cross-view grounding, and viewpoint identification.<n>Our findings demonstrate that language-only reasoning yields marginal improvements, while incorporating visual spatial imagination via a 3D scene imagination pipeline substantially improves cross-view reasoning.
  arXiv  Detail & Related papers  (2026-06-21T12:35:43Z)
• Enhancing Cross-View UAV Geolocalization via LVLM-Driven Relational Modeling [31.36539752384395]
  Cross-view UAV geolocalization aims to identify the exact spatial coordinates of drone-captured imagery by aligning it with extensive, geo-referenced satellite databases.<n>We introduce a novel, plug-and-play ranking architecture designed to explicitly perform joint relational modeling for improved UAV-to-satellite image matching.
  arXiv  Detail & Related papers  (2026-03-09T07:57:29Z)
• TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation [70.23578202012048]
  Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch.<n>We propose TagaVLM (Topology-Aware Global Action reasoning), an end-to-end framework that explicitly injects topological structures into the VLM backbone.<n>To enhance topological node information, an Interleaved Navigation Prompt strengthens node-level visual-text alignment.<n>With the embedded topological graph, the model is capable of global action reasoning, allowing for robust path correction.
  arXiv  Detail & Related papers  (2026-03-03T13:28:07Z)
• STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning [65.36458157092207]
  In vision-language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations.<n>We propose a novel visual prompting paradigm that avoids the difficult problem of aligning coordinates across modalities.<n>We introduce STVG-R1, the first reinforcement learning framework for STVG, which employs a task-driven reward to jointly optimize temporal accuracy, spatial consistency, and structural format regularization.
  arXiv  Detail & Related papers  (2026-02-12T08:53:32Z)
• Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation [38.19842131198389]
  Vision-Language Models (VLMs) leveraging their powerful visual perception and reasoning capabilities have been widely applied in Unmanned Aerial Vehicle (UAV) tasks.<n>However, the spatial intelligence capabilities of existing VLMs in UAV scenarios remain largely unexplored.<n>We introduce SpatialSky-Bench, a benchmark designed to evaluate the spatial intelligence capabilities of VLMs in UAV navigation.
  arXiv  Detail & Related papers  (2025-11-17T11:39:20Z)
• Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models [21.28937516885804]
  We propose a unified benchmark, textbfSpatial-DISE, based on a cognitively grounded taxonomy that categorizes tasks into four fundamental quadrants.<n>To address the issue of data scarcity, we develop a scalable and automated pipeline to generate diverse and verifiable spatial reasoning questions.
  arXiv  Detail & Related papers  (2025-10-15T10:44:01Z)
• SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models [75.64836077468722]
  Vision language models (VLMs) excel in 2D semantic visual understanding, but their ability to quantitatively reason about 3D spatial relationships remains under-explored.<n>We propose SD-VLM, a novel framework that significantly enhances fundamental spatial perception abilities of VLMs.<n>We have trained SD-VLM, a strong generalist VLM which shows superior quantitative spatial measuring and understanding capability.
  arXiv  Detail & Related papers  (2025-09-22T12:08:12Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [68.46716645478661]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• SpaceR: Reinforcing MLLMs in Video Spatial Reasoning [70.7401015322983]
  Video spatial reasoning poses a significant challenge for existing Multimodal Large Language Models (MLLMs)<n>This limitation stems primarily from 1) the absence of high-quality datasets for this task, and 2) the lack of effective training strategies to develop spatial reasoning capabilities.<n>Motivated by the success of Reinforcement Learning with Verifiable Reward (RLVR) in unlocking spatial reasoning abilities, this aims to improve MLLMs in video spatial reasoning through the RLVR paradigm.
  arXiv  Detail & Related papers  (2025-04-02T15:12:17Z)
• Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments [20.69412701553767]
  Unmanned Aerial Vehicles (UAVs) rely on satellite systems for stable positioning. In such situations, vision-based techniques can serve as an alternative, ensuring the self-positioning capability of UAVs. This paper presents a new dataset, DenseUAV, which is the first publicly available dataset designed for the UAV self-positioning task.
  arXiv  Detail & Related papers  (2022-01-23T07:18:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.