DescribeEarth: Describe Anything for Remote Sensing Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Kaiyu, Jiang, Zixuan, Cao, Xiangyong, Wang, Jiayu, Xiao, Yuchen, Meng, Deyu, Wang, Zhi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912616891285504
author Li, Kaiyu
Jiang, Zixuan
Cao, Xiangyong
Wang, Jiayu
Xiao, Yuchen
Meng, Deyu
Wang, Zhi
author_facet Li, Kaiyu
Jiang, Zixuan
Cao, Xiangyong
Wang, Jiayu
Xiao, Yuchen
Meng, Deyu
Wang, Zhi
contents Automated textual description of remote sensing images is crucial for unlocking their full potential in diverse applications, from environmental monitoring to urban planning and disaster management. However, existing studies in remote sensing image captioning primarily focus on the image level, lacking object-level fine-grained interpretation, which prevents the full utilization and transformation of the rich semantic and structural information contained in remote sensing images. To address this limitation, we propose Geo-DLC, a novel task of object-level fine-grained image captioning for remote sensing. To support this task, we construct DE-Dataset, a large-scale dataset contains 25 categories and 261,806 annotated instances with detailed descriptions of object attributes, relationships, and contexts. Furthermore, we introduce DE-Benchmark, a LLM-assisted question-answering based evaluation suite designed to systematically measure model capabilities on the Geo-DLC task. We also present DescribeEarth, a Multi-modal Large Language Model (MLLM) architecture explicitly designed for Geo-DLC, which integrates a scale-adaptive focal strategy and a domain-guided fusion module leveraging remote sensing vision-language model features to encode high-resolution details and remote sensing category priors while maintaining global context. Our DescribeEarth model consistently outperforms state-of-the-art general MLLMs on DE-Benchmark, demonstrating superior factual accuracy, descriptive richness, and grammatical soundness, particularly in capturing intrinsic object features and surrounding environmental attributes across simple, complex, and even out-of-distribution remote sensing scenarios. All data, code and weights are released at https://github.com/earth-insights/DescribeEarth.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25654
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DescribeEarth: Describe Anything for Remote Sensing Images
Li, Kaiyu
Jiang, Zixuan
Cao, Xiangyong
Wang, Jiayu
Xiao, Yuchen
Meng, Deyu
Wang, Zhi
Computer Vision and Pattern Recognition
Automated textual description of remote sensing images is crucial for unlocking their full potential in diverse applications, from environmental monitoring to urban planning and disaster management. However, existing studies in remote sensing image captioning primarily focus on the image level, lacking object-level fine-grained interpretation, which prevents the full utilization and transformation of the rich semantic and structural information contained in remote sensing images. To address this limitation, we propose Geo-DLC, a novel task of object-level fine-grained image captioning for remote sensing. To support this task, we construct DE-Dataset, a large-scale dataset contains 25 categories and 261,806 annotated instances with detailed descriptions of object attributes, relationships, and contexts. Furthermore, we introduce DE-Benchmark, a LLM-assisted question-answering based evaluation suite designed to systematically measure model capabilities on the Geo-DLC task. We also present DescribeEarth, a Multi-modal Large Language Model (MLLM) architecture explicitly designed for Geo-DLC, which integrates a scale-adaptive focal strategy and a domain-guided fusion module leveraging remote sensing vision-language model features to encode high-resolution details and remote sensing category priors while maintaining global context. Our DescribeEarth model consistently outperforms state-of-the-art general MLLMs on DE-Benchmark, demonstrating superior factual accuracy, descriptive richness, and grammatical soundness, particularly in capturing intrinsic object features and surrounding environmental attributes across simple, complex, and even out-of-distribution remote sensing scenarios. All data, code and weights are released at https://github.com/earth-insights/DescribeEarth.
title DescribeEarth: Describe Anything for Remote Sensing Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.25654