# Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery

arXiv: https://arxiv.org/abs/2512.07276 · HTML: https://mlsanity.com/paper/2512.07276/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 83 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 25 of 25)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12384/) (2024)
- [TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data](https://mlsanity.com/paper/2410.06234/) (2024)
- [EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2312.12222/) (2023)
- [GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks](https://mlsanity.com/paper/2411.19325/) (2024)
- [Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation](https://mlsanity.com/paper/2002.01619/) (2020)
- [DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response](https://mlsanity.com/paper/2505.21089/) (2025)
- [DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition](https://mlsanity.com/paper/2302.01791/) (2023)
- [IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network](https://mlsanity.com/paper/1802.10249/) (2018)
- [Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles](https://mlsanity.com/paper/2103.03975/) (2021)
- [HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images](https://mlsanity.com/paper/2301.09460/) (2023)
- [DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding](https://mlsanity.com/paper/2505.21076/) (2025)
- [SGTBN: Generating Dense Depth Maps from Single-Line LiDAR](https://mlsanity.com/paper/2106.12994/) (2021)
- [Enhancing Monocular Height Estimation from Aerial Images with Street-view Images](https://mlsanity.com/paper/2311.02121/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?](https://mlsanity.com/paper/2605.25784/) (2026)

## Abstract (arXiv)

Three-dimensional geospatial analysis is critical for applications in urban planning, climate adaptation, and environmental assessment. However, current methodologies depend on costly, specialized sensors, such as LiDAR and multispectral sensors, which restrict global accessibility. Additionally, existing sensor-based and rule-driven methods struggle with tasks requiring the integration of multiple 3D cues, handling diverse queries, and providing interpretable reasoning. We present Geo3DVQA, a comprehensive benchmark that evaluates vision-language models (VLMs) in height-aware 3D geospatial reasoning from RGB imagery alone. Unlike conventional sensor-based frameworks, Geo3DVQA emphasizes realistic scenarios integrating elevation, sky view factors, and land cover patterns. The benchmark comprises 110k curated question-answer pairs across 16 task categories, including single-feature inference, multi-feature reasoning, and application-level analysis. Through a systematic evaluation of ten state-of-the-art VLMs, we reveal fundamental limitations in RGB-to-3D spatial reasoning. Our results further show that domain-specific instruction tuning consistently enhances model performance across all task categories, including height-aware and open-ended, application-oriented reasoning. Geo3DVQA provides a unified, interpretable framework for evaluating RGB-based 3D geospatial reasoning and identifies key challenges and opportunities for scalable 3D spatial analysis. The code and data are available at https://github.com/mm1129/Geo3DVQA.