Gao, Maggie Y.;Li, Chao;Petzold, Frank;Tiong, Robert L. K.;Yang, Yaowen
Lifecycle framework for AI-driven parametric generative design in industrialized construction
Automation in Construction
2025
174
106146

Memis, Ilayda;Förster, Nick;Petzold, Frank
A Spatial Framework for Human Control in Shared Intelligent Environments
Meta-Responsive Approaches
2025

Förster, Nick;Drechsel, Matti;Schubert, Gerhard;Petzold, Frank
Playful Reconfigurations: Learning, Making, and Playing Geogames for Urban Participation
Urban Planning
2025
11

Pestriakova, Ekaterina;Schubert, Gerhard;Petzold, Frank
Navigating Design Space in the Creative Process: Integrating machine learning for structured exploration avoiding design fixation
2025

Memis, Ilayda;Schubert, Gerhard;Petzold, Frank
Architectural Interfaces for Shared Spaces: A Multi-User Perspective on Intelligent Environment Interactions
CAAD Futures 2025 – Catalytic Interfaces: Conference Proceedings
2025

Wysocki, Olaf;Schwab, Benedikt;Biswanath, Manoj Kumar;Greza, Michael;Zhang, Qilin;Zhu, Jingwei;Froech, Thomas;Heeramaglore, Medhini;Hijazi, Ihab;Kanna, Khaoula;Pechinger, Mathias;Chen, Zhaiyu;Sun, Yao;Segura, Alejandro Rueda;Xu, Ziyang;AbdelGafar, Omar;Mehranfar, Mansour;Yeshwanth, Chandan;Liu, Yueh-Cheng;Yazdi, Hadi;Wang, Jiapan;Auer, Stefan;Anders, Katharina;Bogenberger, Klaus;Borrmann, Andre;Dai, Angela;Hoegner, Ludwig;Holst, Christoph;Kolbe, Thomas H.;Ludwig, Ferdinand;Nießner, Matthias;Petzold, Frank;Zhu, Xiao Xiang;Jutzi, Boris
TUM2TWIN: Introducing the Large-Scale Multimodal Urban Digital Twin Benchmark Dataset
Urban Digital Twins (UDTs) have become essential for managing cities and integrating complex, heterogeneous data from diverse sources. Creating UDTs involves challenges at multiple process stages, including acquiring accurate 3D source data, reconstructing high-fidelity 3D models, maintaining models' updates, and ensuring seamless interoperability to downstream tasks. Current datasets are usually limited to one part of the processing chain, hampering comprehensive UDTs validation. To address these challenges, we introduce the first comprehensive multimodal Urban Digital Twin benchmark dataset: TUM2TWIN. This dataset includes georeferenced, semantically aligned 3D models and networks along with various terrestrial, mobile, aerial, and satellite observations boasting 32 data subsets over roughly 100,000 \$m\textasciicircum2\$ and currently 767 GB of data. By ensuring georeferenced indoor-outdoor acquisition, high accuracy, and multimodal data integration, the benchmark supports robust analysis of sensors and the development of advanced reconstruction methods. Additionally, we explore downstream tasks demonstrating the potential of TUM2TWIN, including novel view synthesis of NeRF and Gaussian Splatting, solar potential analysis, point cloud semantic segmentation, and LoD3 building reconstruction. We are convinced this contribution lays a foundation for overcoming current limitations in UDT creation, fostering new research directions and practical solutions for smarter, data-driven urban environments. The project is available under: https://tum2t.win
2025

Rueda, Alejandro;Sun, Yao;Petzold, Frank
Generation of Annotated Data Using Pre-Trained Diffusion Models: Alleviating the data pain in the context of architectural façade segmentation
ARCHITECTURAL INFORMATICS - Proceedings of the 30th CAADRIA Conference
2025

Drechsel, Matti;Förster, Nick;Schubert, Gerhard;Coutinho, Carolina Meirelles
Where Digital Meets Analog: The Future of Urban Co-Creation
84--99
NEBourhoods for Tomorrow
2025

Wei, Yinyi;Li, Xiao;Petzold, Frank
Text-to-structure interpretation of user requests in BIM interaction
Automation in Construction
2025
174
June
106119