paper-with-me

Papers

EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery

2026-02-17 · Zelin Xu, Yupu Zhang, Saugat Adhikari, Saiful Islam, Tingsong Xiao, Zibo Liu, Shigang Chen, Da Yan, Zhe Jiang arxiv

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical world. However, spatial reasoning on Earth imagery has lagged behind, as it uniquely involves grounding objects in georeferenced images and quantitatively reasoning about distances, directions, and topological relations using both visual cues and vector geometry coordinates (e.g., 2D bounding boxes, polylines, and polygons). Existing benchmarks for Earth imagery primarily focus on 2D spatial grounding, image captioning, and coarse spatial relations (e.g., simple directional or proximity cues). They lack support for quantitative direction and distance reasoning, systematic topological relations, and complex object geometries beyond bounding boxes. To fill this gap, we propose \textbf{EarthSpatialBench}, a comprehensive benchmark for evaluating spatial reasoning in MLLMs on Earth imagery. The benchmark contains over 325K question-answer pairs spanning: (1) qualitative and quantitative reasoning about spatial distance and direction; (2) systematic topological relations; (3) single-object queries, object-pair queries, and compositional aggregate group queries; and (4) object references expressed via textual descriptions, visual overlays, and explicit geometry coordinates, including 2D bounding boxes, polylines, and polygons. We conducted extensive experiments on both open-source and proprietary models to identify limitations in the spatial reasoning of MLLMs.

📄 PDF Abstract BibTeX arXiv:2602.15918

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial ReasoningImage Captioning

Similar Papers 제목 키워드 기반

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

2025-11-22 · Jun Zhang, Xin Zhang, Jie Feng, Long Chen 외 arxiv

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urb…

From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs

2026-05-04 · Le Zhang, Jihan Yang, Soundarya Krishnan, Jimit Majmudar 외 arxiv

Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they are for. While existing benchmarks effectively evaluate the geometric …

Relational ReasoningSpatial Reasoning

AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond

2025-09-30 · Shangding Gu, Xiaohan Wang, Donghao Ying, Haoyu Zhao 외 arxiv

Rapid advances in multimodal models demand benchmarks that rigorously evaluate understanding and reasoning in safety-critical, dynamic real-world settings. We present AccidentBench, a large-scale benchmark that combines …

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models

2025-07-01 · Jiahuan Zhang, Shunwen Bai, Tianheng Wang, Kaiwen Guo 외 arxiv

Humans naturally possess the spatial reasoning ability to form and manipulate images and structures of objects in space. There is an increasing effort to endow Vision-Language Models (VLMs) with similar spatial reasoning…

Spatial Reasoning

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

2024-11-09 · Fatemeh Shiri, Xiao-Yu Guo, Mona Golestan Far, Xin Yu 외

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA d…

object-detectionObject DetectionSpatial ReasoningVisual Question Answering (VQA)