paper-with-me

홈 › Papers

EarthSynth: Generating Informative Earth Observation with Diffusion Models

2025-05-17 · Jiancheng Pan, Shiye Lei, Yuqian Fu, Jiahao Li, Yanxing Liu, Yuze Sun, Xiao He, Long Peng, Xiaomeng Huang, Bo Zhao

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. EarthSynth, trained on the EarthSynth-180K dataset, employs the Counterfactual Composition training strategy 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, offering a practical solution for advancing RSI interpretation.

📄 PDF Abstract BibTeX arXiv:2505.12108

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualDiversityEarth Observationobject-detectionObject DetectionScene ClassificationSemantic Segmentation

Similar Papers 제목 키워드 기반

Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AI

2026-04-02 · Valeria Martin, K. Brent Venable, Derek Morgan arxiv

The scarcity of labeled satellite imagery remains a fundamental bottleneck for deep-learning (DL)-based wildfire monitoring systems. This paper investigates whether a diffusion-based foundation model for Earth Observatio…

Prompt EngineeringData Augmentation

SAR-to-RGB Translation with Latent Diffusion for Earth Observation

2025-04-15 · Kaan Aydin, Joelle Hanna, Damian Borth

Earth observation satellites like Sentinel-1 (S1) and Sentinel-2 (S2) provide complementary remote sensing (RS) data, but S2 images are often unavailable due to cloud cover or data gaps. To address this, we propose a dif…

Cloud RemovalEarth ObservationLand Cover ClassificationTranslation

Data Augmentation in Earth Observation: A Diffusion Model Approach

2024-06-10 · Tiago Sousa, Benoît Ries, Nicolas Guelfi

High-quality Earth Observation (EO) imagery is essential for accurate analysis and informed decision making across sectors. However, data scarcity caused by atmospheric conditions, seasonal variations, and limited geogra…

Data AugmentationDecision MakingDiversityEarth Observation

Diffusion Models for Earth Observation Use-cases: from cloud removal to urban change detection

2023-11-10 · Fulvio Sanguigni, Mikolaj Czerkawski, Lorenzo Papa, Irene Amerini 외

The advancements in the state of the art of generative Artificial Intelligence (AI) brought by diffusion models can be highly beneficial in novel contexts involving Earth observation data. After introducing this new fami…

Change DetectionCloud RemovalDataset GenerationEarth Observation

PreDiff: Precipitation Nowcasting with Latent Diffusion Models

2023-07-19 · NeurIPS 2023 11 · Zhihan Gao, Xingjian Shi, Boran Han, Hao Wang 외

Earth system forecasting has traditionally relied on complex physical models that are computationally expensive and require significant domain expertise. In the past decade, the unprecedented increase in spatiotemporal E…

DenoisingEarth ObservationPrecipitation Forecasting