About
Welcome! I am a Principal Scientist at the Microsoft MR & AI Lab in Zürich and currently visiting CVG at ETH Zürich as an academic guest. Before, I obtained a PhD in Computer Science as part of CVG at ETH Zürich. I received my MSc from UNC Chapel Hill and my BSc from TU Munich.
Research
My main research interests lie in image-based mapping, localization, and scene understanding. More broadly, I am interested in topics at the intersection of computer vision and geometry. A complete and up-to-date list of publications can be found on Google Scholar or further below.
As part of my research, I developed the open-source software COLMAP - an end-to-end image-based 3D reconstruction software that is widely used in academia and industry. Over the years, I also contributed to a number of other scientific open source projects, including scikit-image, scikit-learn, NumPy, SciPy, etc. Most open-source activities can be found on GitHub.
Awards
I received the ECVA Young Researcher Award in 2023 and, for my work on the COLMAP SFM and MVS software, I received the PAMI Mark Everingham Prize in 2020. Further, I received an ETH Medal in 2019 for my PhD thesis as well as a best paper honorable mention at DAGM 2015.
Publications
List of papers and patents in reverse chronological order. For more information, please visit Google Scholar.
Papers
-
Global Structure-from-Motion Revisited
European Conference on Computer Vision (ECCV), 2024
[ Project | Paper | Supplementary | Bibtex | Code ]
-
Robust Incremental Structure-from-Motion with Hybrid Features
European Conference on Computer Vision (ECCV), 2024
[ Paper | Supplementary | Bibtex ]
-
A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction
arXiv, 2023
-
LaMAR: Benchmarking Localization and Mapping for Augmented Reality
European Conference on Computer Vision (ECCV), 2022
-
Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency
International Conference on Robotics and Automation (ICRA), 2022
-
Reconstructing and grounding narrated instructional videos in 3D
arXiv, 2021
-
Cross-Descriptor Visual Localization and Mapping
International Conference on Computer Vision (ICCV), 2021
-
Privacy Preserving Localization and Mapping from Uncalibrated Cameras
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
-
Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[ Paper | Supplementary | Bibtex | Project ]
-
NeuralFusion: Online Depth Fusion in Latent Space
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
-
Multi-View Optimization of Local Feature Geometry
European Conference on Computer Vision (ECCV), 2020
-
Privacy Preserving Structure-from-Motion
European Conference on Computer Vision (ECCV), 2020
-
RoutedFusion: Learning Real-time Depth Map Fusion
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
-
HoloLens 2 Research Mode as a Tool for Computer Vision Research
arXiv, 2020
-
Privacy Preserving Image Queries for Camera Localization
International Conference on Computer Vision (ICCV), 2019
-
Privacy Preserving Image-Based Localization
Conference on Computer Vision and Pattern Recognition (CVPR), 2019
-
SciPy 1.0 - Fundamental Algorithms for Scientific Computing in Python
Nature Methods, 2019
-
Robust Methods for Accurate and Efficient 3D Modeling from Unstructured Imagery
PhD Thesis, 2018
-
Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching
European Conference on Computer Vision (ECCV), 2018
[ Paper | Supplementary | Bibtex ]
-
Learning Priors for Semantic 3D Reconstruction
European Conference on Computer Vision (ECCV), 2018
[ Paper | Supplementary | Bibtex ]
-
VSO: Visual Semantic Odometry
European Conference on Computer Vision (ECCV), 2018
[ Paper | Supplementary | Bibtex ]
-
Semantic Visual Localization
Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[ Paper | Supplementary | Bibtex ]
-
Augmenting Crowd-Sourced 3D Reconstructions using Semantic Detections
Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[ Paper | Supplementary | Bibtex ]
-
Comparative Evaluation of Hand-Crafted and Learned Local Features
Conference on Computer Vision and Pattern Recognition (CVPR), 2017
[ Benchmark | Paper | Supplementary | Bibtex ]
-
A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos
Conference on Computer Vision and Pattern Recognition (CVPR), 2017
[ Paper | Supplementary | Bibtex ]
-
Mapping on the Fly: Real-Time 3D Dense Reconstruction, Digital Surface Map and Incremental Orthomosaic Generation for Unmanned Aerial Vehicles
International Conference on Field and Service Robotics (FSR), 2017
[ Code | Paper | Supplementary | Bibtex ]
-
A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval
Asian Conference on Computer Vision (ACCV), 2016
[ Code | Paper | Supplementary | Bibtex ]
-
Pixelwise View Selection for Unstructured Multi-View Stereo
European Conference on Computer Vision (ECCV), 2016
[ Paper | Supplementary | Bibtex | Video ]
-
Indoor-Outdoor 3D Reconstruction Alignment
European Conference on Computer Vision (ECCV), 2016
[ Paper | Supplementary | Bibtex | Video ]
-
Structure-from-Motion Revisited
Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[ Website | Paper | Supplementary | Bibtex | Video ]
-
From Dusk till Dawn: Modeling in the Dark
Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[ Paper | Supplementary | Bibtex | Video ]
-
Efficient Two-View Geometry Classification
German Conference on Pattern Recognition (GCPR), 2015
-
PAIGE: PAirwise Image Geometry Encoding for Improved Efficiency in Structure-from-Motion
Conference on Computer Vision and Pattern Recognition (CVPR), 2015
-
From Single Image Query to Detailed 3D Reconstruction
Conference on Computer Vision and Pattern Recognition (CVPR), 2015
-
Reconstructing the World* in Six Days *(As Captured by the Yahoo 100 Million Image Dataset)
Conference on Computer Vision and Pattern Recognition (CVPR), 2015
-
scikit-image: Image processing in Python
PeerJ, 2014
-
Structure-from-motion for MAV image sequence analysis with photogrammetric applications
Photogrammetric Computer Vision Symposium (PCV), 2014
-
Benefit of Using Multiple Baselines and Multiple Aspects for SAR Interferometry of Urban Areas
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2014
-
Adaptive Covariance Matrix Estimation for Multi-Baseline InSAR Data Stacks
IEEE Transactions on Geoscience and Remote Sensing (TGARS), 2014
-
Potential of Airborne Single-Pass Millimeterwave InSAR Data for Individual Tree Recognition
33. Wissenschaftlich Technische Jahrestagung der DGPF, 2013
Patents
-
Matching Between 2D And 3D For Direct Localization
US Patent App. 18/055,722, 2024
-
Access Authentication Using Obfuscated Biometrics
US Patent App. 17/997,081, 2023
-
Collecting Telemetry Data for 3D Map Updates
US Patent App. 17/751,193, 2023
-
Updating a 3D Map of an Environment
US Patent App. 17/743,430, 2023
-
Facade Biasing for Reflection Correction in Photogrammetric Reconstruction
WO 2023 023266 A1, 2023
-
Image-based Localization
US Patent 11,145,083, 2021
-
Fusing Disparity Proposals in Stereo Matching
US Patent 10,878,590, 2020
-
Methods, Systems, and Computer Readable Media for Image Overlap Detection
US Patent 10,504,000, 2018
Miscellaneous
Selected Talks, Workshops, Tutorials
- ECCV 2022, Co-organizer, “Tutorial on Localization and Mapping for Augmented Reality”
- CVPR 2020/2021/2022, Co-organizer, “Image Matching: Local Features & Beyond”
- CVPR2019/2020, ECCV2020, Co-organizer, “Long-Term Visual Localization Benchmark”
- ECCV 2020, Co-organizer, Los Angeles, “Microsoft HoloLens 2 and Azure Kinect DK as Tools for Computer Vision Research”
- CVPR 2019, 3D Scene Generation, Speaker, Los Angeles, “3D Scene Reconstruction from Unstructured Imagery”
- CVPR 2019, Co-organizer, Los Angeles, “Computer Vision Applications for Mixed Reality Headsets”
- CVPR 2018, Robust Vision Challenge, Co-organizer and Speaker, Salt Lake City, “Robust and Accurate Image-Based 3D Modeling”
- CVPR 2018, Co-organizer, Los Angeles, “HoloLens as a Tool for Computer Vision Research”
- Microsoft Research AI 2018, Speaker, Redmond, “Efficient and Accurate Image-Based 3D Modeling”
- CVPR 2017, Co-organizer and Speaker, Hawaii, “Tutorial: Large-scale 3D Modeling from Crowdsourced Data”
- 3DV 2016, Co-organizer and Speaker, Stanford University, “Tutorial: Large-scale 3D Modeling from Crowdsourced Data”
- GCPR 2015, Speaker, RWTH Aachen, “Efficient Two-View Geometry Classification”
- CMP 2015, Speaker, CVUT Prague, “PAIGE: PAirwise Image Geometry Encoding for Improved Efficiency in Structure-from-Motion”