EUVIMEDEUVIMED entdecken
Crossref

MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation

Zhiping Yu, Chenyang Liu, Liqin Liu, Zhenwei Shi, Zhengxia Zou

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-03 · 47 (3) · 1764-1781

DOI: 10.1109/tpami.2024.3507010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-03. Verfasst von Zhiping Yu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The recent advancement of generative foundational models has ushered in a new era of image generation in the realm of natural images, revolutionizing art design, entertainment, environment simulation, and beyond. Despite producing high-quality samples, existing methods are constrained to generating images of scenes at a limited scale. In this paper, we present MetaEarth - a generative foundation model that breaks the barrier by scaling image generation to a global level, exploring the creation of worldwide, multi-resolution, unbounded, and virtually limitless remote sensing images. In MetaEarth, we propose a resolution-guided self-cascading generative framework, which enables the generating of images at any region with a wide range of geographical resolutions. To achieve unbounded and arbitrary-sized image generation, we design a novel noise sampling strategy for denoising diffusion models by analyzing the generation conditions and initial noise. To train MetaEarth, we construct a large dataset comprising multi-resolution optical remote sensing images with geographical information. Experiments have demonstrated the powerful capabilities of our method in generating global-scale images. Additionally, the MetaEarth serves as a data engine that can provide high-quality and rich training data for downstream tasks. Our model opens up new possibilities for constructing generative world models by simulating Earth's visuals from an innovative overhead perspective.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Beijing Natural Science Foundation
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Yu, Z., Liu, C., Liu, L., Shi, Z., & Zou, Z. (2025). MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(3), 1764-1781. https://doi.org/10.1109/tpami.2024.3507010

Vancouver

Yu Z, Liu C, Liu L, Shi Z, Zou Z. MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(3):1764-1781. doi:10.1109/tpami.2024.3507010

BibTeX
@article{Yu2025,
  author = {Yu, Zhiping and Liu, Chenyang and Liu, Liqin and Shi, Zhenwei and Zou, Zhengxia},
  title = {MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {3},
  pages = {1764--1781},
  doi = {10.1109/tpami.2024.3507010}
}
Kostenlos starten →