EarthSynth: Generating Informative Earth Observation with Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Jiancheng, Lei, Shiye, Fu, Yuqian, Li, Jiahao, Liu, Yanxing, Sun, Yuze, He, Xiao, Peng, Long, Huang, Xiaomeng, Zhao, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909726096228352
author Pan, Jiancheng
Lei, Shiye
Fu, Yuqian
Li, Jiahao
Liu, Yanxing
Sun, Yuze
He, Xiao
Peng, Long
Huang, Xiaomeng
Zhao, Bo
author_facet Pan, Jiancheng
Lei, Shiye
Fu, Yuqian
Li, Jiahao
Liu, Yanxing
Sun, Yuze
He, Xiao
Peng, Long
Huang, Xiaomeng
Zhao, Bo
contents Remote sensing image (RSI) interpretation typically faces challenges due to the scarcity of labeled data, which limits the performance of RSI interpretation tasks. To tackle this challenge, we propose EarthSynth, a diffusion-based generative foundation model that enables synthesizing multi-category, cross-satellite labeled Earth observation for downstream RSI interpretation tasks. To the best of our knowledge, EarthSynth is the first to explore multi-task generation for remote sensing, tackling the challenge of limited generalization in task-oriented synthesis for RSI interpretation. EarthSynth, trained on the EarthSynth-180K dataset, employs the Counterfactual Composition training strategy with a three-dimensional batch-sample selection mechanism to improve training data diversity and enhance category control. Furthermore, a rule-based method of R-Filter is proposed to filter more informative synthetic data for downstream tasks. We evaluate our EarthSynth on scene classification, object detection, and semantic segmentation in open-world scenarios. There are significant improvements in open-vocabulary understanding tasks, offering a practical solution for advancing RSI interpretation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EarthSynth: Generating Informative Earth Observation with Diffusion Models
Pan, Jiancheng
Lei, Shiye
Fu, Yuqian
Li, Jiahao
Liu, Yanxing
Sun, Yuze
He, Xiao
Peng, Long
Huang, Xiaomeng
Zhao, Bo
Computer Vision and Pattern Recognition
Artificial Intelligence
Remote sensing image (RSI) interpretation typically faces challenges due to the scarcity of labeled data, which limits the performance of RSI interpretation tasks. To tackle this challenge, we propose EarthSynth, a diffusion-based generative foundation model that enables synthesizing multi-category, cross-satellite labeled Earth observation for downstream RSI interpretation tasks. To the best of our knowledge, EarthSynth is the first to explore multi-task generation for remote sensing, tackling the challenge of limited generalization in task-oriented synthesis for RSI interpretation. EarthSynth, trained on the EarthSynth-180K dataset, employs the Counterfactual Composition training strategy with a three-dimensional batch-sample selection mechanism to improve training data diversity and enhance category control. Furthermore, a rule-based method of R-Filter is proposed to filter more informative synthetic data for downstream tasks. We evaluate our EarthSynth on scene classification, object detection, and semantic segmentation in open-world scenarios. There are significant improvements in open-vocabulary understanding tasks, offering a practical solution for advancing RSI interpretation.
title EarthSynth: Generating Informative Earth Observation with Diffusion Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.12108