Publications

The TUM2TWIN datasets were utilized in the following works and publications so far:

• ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset, WACV ‘25 IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
• Reviewing Open Data Semantic 3D City Models to Develop Novel 3D Reconstruction Methods, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2024
• PolyGNN: Polyhedron-based graph neural network for 3D building reconstruction from point clouds, ISPRS Journal of Photogrammetry and Remote Sensing, 2024
• A framework for fully automated reconstruction of semantic building model at urban-scale using textured LoD2 data, ISPRS Journal of Photogrammetry and Remote Sensing, 2024
• Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks, CVPRW ‘23 proceedings, 2023
• Automatisierte Generierung eines Baumkatasters aus Punktwolken in unterschiedlichen urbanen Umgebungen, Master’s thesis, Technichal University of Munich, Github Repository, 2023
• Thermal Mapping from Point Clouds to 3D Building Model Facades, Remote Sensing journal, 2023
• Evaluation of the Effect of Enriched Facade Models on Image-Based Localization of Vehicles, Bachelor’s thesis, Technical University of Munich, Github Repository, 2023
• Reconstructing Façade Details Using MLS Point Clouds and Bag-of-Words Approach , 3DGeoInfo ‘23 proceedings, 2023
• Inpainting of unseen façade objects using deep learning methods, Master’s thesis, Technical University of Munich, 2023
• TUM-FAÇADE: Reviewing and enriching point cloud benchmarks for façade segmentation, ISPRS Archives, ArCH ‘22 proceedings, 2022