MetaEarth3D: Unlocking World-scale 3D Generation with Spatially Scalable Generative Modeling

TL;DR

MetaEarth3D introduces a groundbreaking generative model capable of creating spatially consistent 3D scenes at a planetary scale, advancing Earth observation and large-scale spatial understanding.

Contribution

It is the first model to incorporate spatial scale as a core dimension, enabling ultra-wide-area 3D generation across diverse terrains and urban environments.

Findings

Generated 3D scenes are both visually and geospatially realistic.

MetaEarth3D can produce unbounded, multi-level terrains and urban environments.

Built on 10 million real-world images, it demonstrates strong realism and diversity.

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 the planetary 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 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.