SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model Article Swipe

MAKE IMPACT

Kaiyu Li , Zepeng Xin , Pang Li , Chao Pang , Yupeng Deng , Jing Yao , Gui-Song Xia , Deyu Meng , Zhi Wang , Xiangyong Cao · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2504.09644

Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to handle complex, implicit queries that require reasoning over spatial context, domain knowledge, and implicit user intent. Motivated by this, we introduce a new task, \ie, geospatial pixel reasoning, which allows implicit querying and reasoning and generates the mask of the target region. To advance this task, we construct and release the first large-scale benchmark dataset called EarthReason, which comprises 5,434 manually annotated image masks with over 30,000 implicit question-answer pairs. Moreover, we propose SegEarth-R1, a simple yet effective language-guided segmentation baseline that integrates a hierarchical visual encoder, a large language model (LLM) for instruction parsing, and a tailored mask generator for spatial correlation. The design of SegEarth-R1 incorporates domain-specific adaptations, including aggressive visual token compression to handle ultra-high-resolution remote sensing images, a description projection module to fuse language and multi-scale features, and a streamlined mask prediction pipeline that directly queries description embeddings. Extensive experiments demonstrate that SegEarth-R1 achieves state-of-the-art performance on both reasoning and referring segmentation tasks, significantly outperforming traditional and LLM-based segmentation methods. Our data and code will be released at https://github.com/earth-insights/SegEarth-R1.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2504.09644

PDF

https://arxiv.org/pdf/2504.09644

OA Status

green

Cited By

1

OpenAlex ID

https://openalex.org/W4415158162

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415158162

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2504.09644

Digital Object Identifier

Title

SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-04-13

Full publication date if available

Authors

Kaiyu Li, Zepeng Xin, Pang Li, Chao Pang, Yupeng Deng, Jing Yao, Gui-Song Xia, Deyu Meng, Zhi Wang, Xiangyong Cao

List of authors in order

Landing page

https://arxiv.org/abs/2504.09644

Publisher landing page

PDF URL

https://arxiv.org/pdf/2504.09644

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2504.09644

Direct OA link when available

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2025: 1

Per-year citation counts (last 5 years)

Full payload