Home  | News

04.12.2025

Teaser image to World’s First Complete 3D Model of All Buildings Released

World’s First Complete 3D Model of All Buildings Released

TUM News

A research team led by MCML PI Xiaoxiang Zhu has released the GlobalBuildingAtlas, the first global high-resolution 3D model of all buildings on Earth.

Based on 2019 satellite data, the atlas includes more than 2.75 billion buildings worldwide. It offers a ground-breaking spatial resolution of 3×3 meters, providing up to 30 times more detail than previous global datasets. Over 97% of all buildings are available as standardized LoD1 3D models, enabling precise analyses of urbanization, infrastructure, disaster response, and climate-impact scenarios.

The GlobalBuildingAtlas marks a major step forward for open science and global-scale geospatial analysis, offering unprecedented data quality for researchers, policymakers, and planners.

#research #zhu
Subscribe to RSS News feed

Related

Link to When to Say "I’m Not Sure": Making Language Models More Self-Aware

04.12.2025

When to Say "I’m Not Sure": Making Language Models More Self-Aware

ICLR 2025 research by the groups of David Rügamer, and Bernd Bischl introduces methods to make LLMs more reliable by expressing uncertainty.

Link to

28.11.2025

MCML at NeurIPS 2025

MCML researchers are represented with 46 papers at NeurIPS 2025 (37 Main, and 9 Workshops).

Link to Seeing the Bigger Picture – One Detail at a Time

27.11.2025

Seeing the Bigger Picture – One Detail at a Time

FLAIR, introduced by Zeynep Akata’s group at CVPR 2025, brings fine-grained, text-guided detail recognition to vision-language models.

Link to Daniel Rückert Among the World’s Most Cited Researchers

25.11.2025

Daniel Rückert Among the World’s Most Cited Researchers

MCML Director Daniel Rückert is among the world’s most cited researchers for AI in healthcare, part of 17 TUM scientists recognized in 2025.

Link to Zigzag Your Way to Faster, Smarter AI Image Generation

20.11.2025

Zigzag Your Way to Faster, Smarter AI Image Generation

ZigMa, introduced by Björn Ommer’s group at ECCV 24, improves high-res AI image and video generation with fast, memory-efficient zigzag scanning.

Back to Top