Olaf Wysocki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Olaf Wysocki has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
- Uwe Stilla
Technical University of Munich (TUM)
14 shared publications - Ludwig Hoegner
Department of Geoinformatics, Hochschule München University of Applied Sciences, Munich, Germany
12 shared publications - Boris Jutzi
Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
7 shared publications - Christoph Holst
Chair of Engineering Geodesy, TUM School of Engineering and Design, Technical University of Munich, Munich, Germany
7 shared publications - Qilin Zhang
Photogrammetry and Remote Sensing, TUM School of Engineering and Design, Technical University of Munich (TUM), Munich, Germany
6 shared publications - Daniel Cremers
Technical University of Munich
5 shared publications
Latest Publications
- 3 October 2026
- Published by Springer Nature
- p. 508-526
SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models
- 3 October 2026
- Published by Springer Nature
- p. 508-526
SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 11593-11600
TOL: Textual Localization With OpenStreetMap
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 11593-11600
TOL: Textual Localization With OpenStreetMap
- 12 September 2026
- Published by Springer Nature
- p. 55-73
OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
- 12 September 2026
- Published by Springer Nature
- p. 55-73
OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
- Open Access
- 29 July 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 240, 184-201
GeoGS: Geometric Prior-Guided Gaussian Splatting for robust urban reconstruction from sparse views
- 29 July 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 240, 184-201
Open AccessGeoGS: Geometric Prior-Guided Gaussian Splatting for robust urban reconstruction from sparse views
- Open Access
- 3 July 2026
- Published by Copernicus GmbH in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XI-2-2026, 411-418
CityLangSplat: Integrating CityGML Semantics into 3D Language Gaussian Splatting for Urban Scene Understanding
Combining visual semantics with language representations has made 3D interpretation more flexible and intuitive. Recent advances in Gaussian Splatting extend this to efficient 3D language fields supporting open-vocabulary queries. However, existing approaches show limited generalization in large urban scenes, especially for detailed building segmentation. Semantic 3D city models such as CityGML, by contrast, provide hierarchical and geometry-aligned structural semantics that complement appearance-driven visual cues. We introduce CityLangSplat, which integrates CityGML semantics into 3D Language Gaussian Splatting for urban environments. CityLangSplat rasterizes CityGML into pixel-aligned semantic maps, extracts vision-language features from SAM-derived segments and CityGML regions, and compresses both sources into a shared latent space via a lightweight autoencoder. 3D Gaussians are then optimized with a coverage-aware loss that balances accurate, building-focused CityGML supervision with broader SAM supervision, enabling geometry-aligned open-vocabulary reasoning in urban scenes. Experiments on TUM2TWIN and ZAHA datasets show consistent gains over LangSplat, with relative improvements of 22.9% in 2D and 15.1% in 3D evaluation while preserving real-time rendering. CityLangSplat provides a practical framework for combining semantic city models with language-embedded 3D Gaussian Splatting for geometry-aligned urban scene interpretation. Code will be released at https://github.com/zqlin0521/CityLangSplat.
- 3 July 2026
- Published by Copernicus GmbH in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XI-2-2026, 411-418
Open AccessCityLangSplat: Integrating CityGML Semantics into 3D Language Gaussian Splatting for Urban Scene Understanding
Combining visual semantics with language representations has made 3D interpretation more flexible and intuitive. Recent advances in Gaussian Splatting extend this to efficient 3D language fields supporting open-vocabulary queries. However, existing approaches show limited generalization in large urban scenes, especially for detailed building segmentation. Semantic 3D city models such as CityGML, by contrast, provide hierarchical and geometry-aligned structural semantics that complement appearance-driven visual cues. We introduce CityLangSplat, which integrates CityGML semantics into 3D Language Gaussian Splatting for urban environments. CityLangSplat rasterizes CityGML into pixel-aligned semantic maps, extracts vision-language features from SAM-derived segments and CityGML regions, and compresses both sources into a shared latent space via a lightweight autoencoder. 3D Gaussians are then optimized with a coverage-aware loss that balances accurate, building-focused CityGML supervision with broader SAM supervision, enabling geometry-aligned open-vocabulary reasoning in urban scenes. Experiments on TUM2TWIN and ZAHA datasets show consistent gains over LangSplat, with relative improvements of 22.9% in 2D and 15.1% in 3D evaluation while preserving real-time rendering. CityLangSplat provides a practical framework for combining semantic city models with language-embedded 3D Gaussian Splatting for geometry-aligned urban scene interpretation. Code will be released at https://github.com/zqlin0521/CityLangSplat.
- Open Access
- 3 July 2026
- Published by Copernicus GmbH in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XI-2-2026, 293-302
GT-LOD3: LOD3 Semantic 3D Building Reconstruction Benchmark Dataset
Reconstructing semantic 3D building models at level of detail 3 (LOD3) is a long-standing challenge in photogrammetry, remote sensing, and computer vision. In contrast to conventional mesh-based representations, LOD3 models require watertight geometries along with semantic object-level facade elements. In GT-LOD3, we introduce the first LOD3 building benchmark dataset comprising point clouds and images paired with 32 ground truth (GT) LOD3 instances in two different countries. We also analyze the performance of selected baselines, complemented by a discussion on unresolved challenges. We are convinced that GT-LOD3 will facilitate the development of novel LOD3 reconstruction methods, enabling the widespread adoption of LOD3 models and, consequently, various downstream applications, ranging from energy demand estimation to automated driving function testing. We release the dataset as open-source and it can be accessed at https://github.com/gdslab/GT-LOD3-Benchmark
- 3 July 2026
- Published by Copernicus GmbH in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XI-2-2026, 293-302
Open AccessGT-LOD3: LOD3 Semantic 3D Building Reconstruction Benchmark Dataset
Reconstructing semantic 3D building models at level of detail 3 (LOD3) is a long-standing challenge in photogrammetry, remote sensing, and computer vision. In contrast to conventional mesh-based representations, LOD3 models require watertight geometries along with semantic object-level facade elements. In GT-LOD3, we introduce the first LOD3 building benchmark dataset comprising point clouds and images paired with 32 ground truth (GT) LOD3 instances in two different countries. We also analyze the performance of selected baselines, complemented by a discussion on unresolved challenges. We are convinced that GT-LOD3 will facilitate the development of novel LOD3 reconstruction methods, enabling the widespread adoption of LOD3 models and, consequently, various downstream applications, ranging from energy demand estimation to automated driving function testing. We release the dataset as open-source and it can be accessed at https://github.com/gdslab/GT-LOD3-Benchmark
- Open Access
- 1 July 2026
- Published by Copernicus GmbH in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XI-1-2026, 463-471
From Propagation to Prediction: Point-level Uncertainty Evaluation of MLS Point Clouds under Limited Ground Truth
Evaluating uncertainty is critical for reliable use of Mobile Laser Scanning (MLS) point clouds in many high-precision applications such as Scan-to-BIM, deformation analysis, and 3D modeling. However, obtaining the ground truth (GT) for evaluation is often costly and infeasible in many real-world applications. To reduce this long-standing reliance on GT in uncertainty evaluation research, this study presents a learning-based framework for MLS point clouds that integrates optimal neighborhood estimation with geometric feature extraction. Experiments on a real-world dataset show that the proposed framework is feasible and the XGBoost model delivers fully comparable accuracy to Random Forest while achieving substantially higher efficiency (about 3 times faster), providing initial evidence that geometric features can be used to predict point-level uncertainty quantified by the C2C distance. In summary, this study shows that MLS point clouds’ uncertainty is learnable, offering a novel learning-based viewpoint towards uncertainty evaluation research.
- 1 July 2026
- Published by Copernicus GmbH in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XI-1-2026, 463-471
Open AccessFrom Propagation to Prediction: Point-level Uncertainty Evaluation of MLS Point Clouds under Limited Ground Truth
Evaluating uncertainty is critical for reliable use of Mobile Laser Scanning (MLS) point clouds in many high-precision applications such as Scan-to-BIM, deformation analysis, and 3D modeling. However, obtaining the ground truth (GT) for evaluation is often costly and infeasible in many real-world applications. To reduce this long-standing reliance on GT in uncertainty evaluation research, this study presents a learning-based framework for MLS point clouds that integrates optimal neighborhood estimation with geometric feature extraction. Experiments on a real-world dataset show that the proposed framework is feasible and the XGBoost model delivers fully comparable accuracy to Random Forest while achieving substantially higher efficiency (about 3 times faster), providing initial evidence that geometric features can be used to predict point-level uncertainty quantified by the C2C distance. In summary, this study shows that MLS point clouds’ uncertainty is learnable, offering a novel learning-based viewpoint towards uncertainty evaluation research.
- Open Access
- 27 March 2026
- Published by Elsevier in Automation in Construction
- Vol. 187
Tunnel scanner: Geometry-informed synthetic point cloud generation and transfer learning for tunnel segmentation
- 27 March 2026
- Published by Elsevier in Automation in Construction
- Vol. 187
Open AccessTunnel scanner: Geometry-informed synthetic point cloud generation and transfer learning for tunnel segmentation
- Top Cited PapersOpen Access
- 13 January 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 232, 810-830
TUM2TWIN: Introducing the large-scale multimodal urban digital twin benchmark dataset
- 13 January 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 232, 810-830
Top Cited PapersOpen AccessTUM2TWIN: Introducing the large-scale multimodal urban digital twin benchmark dataset