Remote Sensing-Oriented World Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Yuxi, Wu, Biao, Li, Zhidong, Li, Kunqi, Huang, Chenya, Wang, Huacan, Lan, Qizhen, Chen, Ronghao, Chen, Ling, Liang, Bin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914174335975424
author Lu, Yuxi
Wu, Biao
Li, Zhidong
Li, Kunqi
Huang, Chenya
Wang, Huacan
Lan, Qizhen
Chen, Ronghao
Chen, Ling
Liang, Bin
author_facet Lu, Yuxi
Wu, Biao
Li, Zhidong
Li, Kunqi
Huang, Chenya
Wang, Huacan
Lan, Qizhen
Chen, Ronghao
Chen, Ling
Liang, Bin
contents World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene settings, limiting their validation in real-world contexts with broad spatial coverage and complex semantics. Meanwhile, remote sensing applications urgently require spatial reasoning capabilities for disaster response and urban planning. This paper bridges these gaps by introducing the first framework for world modeling in remote sensing. We formulate remote sensing world modeling as direction-conditioned spatial extrapolation, where models generate semantically consistent adjacent image tiles given a central observation and directional instruction. To enable rigorous evaluation, we develop RSWISE (Remote Sensing World-Image Spatial Evaluation), a benchmark containing 1,600 evaluation tasks across four scenarios: general, flood, urban, and rural. RSWISE combines visual fidelity assessment with instruction compliance evaluation using GPT-4o as a semantic judge, ensuring models genuinely perform spatial reasoning rather than simple replication. Afterwards, we present RemoteBAGEL, a unified multimodal model fine-tuned on remote sensing data for spatial extrapolation tasks. Extensive experiments demonstrate that RemoteBAGEL consistently outperforms state-of-the-art baselines on RSWISE.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17808
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Remote Sensing-Oriented World Model
Lu, Yuxi
Wu, Biao
Li, Zhidong
Li, Kunqi
Huang, Chenya
Wang, Huacan
Lan, Qizhen
Chen, Ronghao
Chen, Ling
Liang, Bin
Machine Learning
F.2.2; I.2.7
World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene settings, limiting their validation in real-world contexts with broad spatial coverage and complex semantics. Meanwhile, remote sensing applications urgently require spatial reasoning capabilities for disaster response and urban planning. This paper bridges these gaps by introducing the first framework for world modeling in remote sensing. We formulate remote sensing world modeling as direction-conditioned spatial extrapolation, where models generate semantically consistent adjacent image tiles given a central observation and directional instruction. To enable rigorous evaluation, we develop RSWISE (Remote Sensing World-Image Spatial Evaluation), a benchmark containing 1,600 evaluation tasks across four scenarios: general, flood, urban, and rural. RSWISE combines visual fidelity assessment with instruction compliance evaluation using GPT-4o as a semantic judge, ensuring models genuinely perform spatial reasoning rather than simple replication. Afterwards, we present RemoteBAGEL, a unified multimodal model fine-tuned on remote sensing data for spatial extrapolation tasks. Extensive experiments demonstrate that RemoteBAGEL consistently outperforms state-of-the-art baselines on RSWISE.
title Remote Sensing-Oriented World Model
topic Machine Learning
F.2.2; I.2.7
url https://arxiv.org/abs/2509.17808