ABot-Earth 0.5: Generative 3D Earth Model

Hugging Face Daily Papers Papers

Summary

ABot-Earth 0.5 is a generative 3D framework that synthesizes realistic 3D urban environments from satellite imagery using 3D Gaussian Splatting, enabling real-time visualization and closed-loop UAV navigation at low cost.

We present ABot-Earth 0.5, a generative 3D framework designed to synthesize vast, seamless 3D environments from ubiquitous, geospatially referenced satellite imagery. To achieve this, we propose a novel generative model formulated directly with the 3D Gaussian Splatting (3DGS) representation. The model is trained on a diverse corpus of existing real-world urban reconstructions, learning to generate realistic geometry and textures. At inference, it synthesizes novel 3D scenes conditioned solely on satellite imagery at a scalable rate of under 10 minutes per square kilometer, while demonstrating exceptional realism. The framework is designed for accessibility, with integrated hierarchical level-of-detail (LOD) structures that permit real-time, interactive visualization on web-based map engines. This high-fidelity simulation sandbox effectively mitigates the sim-to-real domain gap, enabling critical downstream Embodied AI applications like closed-loop UAV navigation. By providing an ultra-low-cost and high-efficiency solution, ABot-Earth 0.5 significantly lowers the technical and financial barriers to large-scale 3D reconstruction and empowers the future of global digital earth visualization.
Original Article
View Cached Full Text

Cached at: 06/10/26, 05:45 AM

Paper page - ABot-Earth 0.5: Generative 3D Earth Model

Source: https://huggingface.co/papers/2606.09967 Published on Jun 8

#1 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

ABot-Earth 0.5 generates realistic 3D environments from satellite imagery using 3D Gaussian Splatting representation, enabling fast synthesis and real-time visualization for Embodied AI applications.

We present ABot-Earth 0.5, a generative 3D framework designed to synthesize vast, seamless 3D environments from ubiquitous, geospatially referencedsatellite imagery. To achieve this, we propose a novelgenerative modelformulated directly with the3D Gaussian Splatting(3DGS) representation. The model is trained on a diverse corpus of existing real-world urban reconstructions, learning to generate realistic geometry and textures. At inference, it synthesizes novel 3D scenes conditioned solely onsatellite imageryat a scalable rate of under 10 minutes per square kilometer, while demonstrating exceptional realism. The framework is designed for accessibility, with integrated hierarchicallevel-of-detail(LOD) structures that permit real-time, interactive visualization on web-based map engines. This high-fidelity simulation sandbox effectively mitigates the sim-to-real domain gap, enabling critical downstreamEmbodied AIapplications like closed-loopUAV navigation. By providing an ultra-low-cost and high-efficiency solution, ABot-Earth 0.5 significantly lowers the technical and financial barriers to large-scale 3D reconstruction and empowers the future of globaldigital earth visualization.

View arXiv pageView PDFProject pageGitHub83Add to collection

Get this paper in your agent:

hf papers read 2606\.09967

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.09967 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.09967 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.09967 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Hugging Face Daily Papers

Sat3DGen introduces a geometry-first approach for generating street-level 3D scenes from a single satellite image, achieving improved geometric accuracy and photorealism through novel constraints and training strategies. The method demonstrates significant improvements over prior work on the VIGOR-OOD benchmark.