NERF2BIM
AI-Driven Detailing-on-Demand through Sustainable Point Cloud Surveys and Semantic 3D Understanding for Advanced Modeling of Existing Buildings
Principal Investigators
Prof. Dr.-Ing. Frank Petzold
Chair of Architectural Informatics, TUM School of Engineering and Design
Prof. Dr.-Ing. Matthias Niessner
Chair of Visual Computing and Artificial Intelligence, TUM School of Computation, Information and Technology
Prof. Dr.-Ing. Christoph Holst
Chair of Engineering Geodesy, TUM School of Engineering and Design
Motivation and Goals
The renovation and retrofitting of the built environment requires highly detailed model of the built environment. This project involves the generation of a detailing on demand system of the built environment involving the generation of high-quality 3D geometrical and color scanning, the reconstruction of the geometry and semantics, predicting the likely BIM element types and reconstructing them into complete BIM Models, utilizing a knowledge base of construction principals, also providing detailing to the existing elements.
