MetaEarth3D: Spatially Scalable Generative Modeling for World-scale 3D Scenes

Clicks: 4
ID: 332492
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #376 of 383 articles by views in national science review

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 383 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Abstract Recent generative AI models have achieved remarkable breakthroughs in language and visual understanding. However, although these models can generate realistic visual content, their spatial scale remains confined to bounded environments, preventing them from capturing how geographic environments evolve across thousands of kilometers or from modeling the spatial structure of the large-scale physical world. This limitation poses a critical challenge for ultra-wide-area spatial intelligence in Earth observation and simulation, revealing a deeper gap in generative AI: progress has relied primarily on scaling model parameters and training data, while overlooking spatial scale as a core dimension of intelligence. Here, motivated by this missing dimension, we investigate spatial scale as a new scaling axis in foundation models and present MetaEarth3D, the first generative foundation model capable of spatially consistent generation at world scale. Taking optical Earth observation simulation as a testbed, MetaEarth3D enables the generation of multi-level, unbounded, and diverse 3D scenes spanning large-scale terrains, medium-scale cities, and fine-grained street blocks. Built upon 10.2 million globally distributed real-world training images, MetaEarth3D demonstrates both strong visual realism and geospatial statistical realism. Beyond generation, MetaEarth3D serves as a generative data engine for diverse virtual environments in ultra-wide spatial intelligence. We argue that this study may help empower next-generation spatial intelligence for Earth observation.
Reference Key
openalex_W7222211387 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Jinqi Cao, Zhiping Yu, Baihong Lin, Chenyang Liu, Zhenwei Shi, Zhengxia Zou
Journal national science review
Year 2026
DOI
10.1093/nsr/nwag648
URL
https://doi.org/10.1093/nsr/nwag648
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.