Johannes Schönberger

About

I am an engineer and researcher in the Reality AI Research team at Meta in Zurich. Previously, I spent 6 years as a Principal Scientist at the Microsoft MR & AI Lab and received my PhD in Computer Science with the CVG group at ETH Zürich.

Research

My main research interests lie in image-based mapping, localization, and scene understanding. More broadly, I work at the intersection of computer vision and geometry. For a complete, up-to-date list, see Google Scholar or the list below.

As part of my research, I developed COLMAP — an end-to-end image-based 3D reconstruction pipeline widely used in academia and industry. I have also contributed to several other open-source scientific projects, including scikit-image, scikit-learn, NumPy, and SciPy. See GitHub for more.

Awards

I received the ECVA Young Researcher Award in 2023 and, for my work on the COLMAP SfM and MVS pipeline, the PAMI Mark Everingham Prize in 2020. In 2019, I received an ETH Medal for my PhD thesis. Earlier, my work received an honorable mention for best paper at DAGM 2015.

Publications

Reverse chronological list of papers. See Google Scholar for citation counts and a complete list.

2026

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Nikhil Keetha, Norman Müller, Johannes Schönberger, Lorenzo Porzi, Yuchen Zhang, Tobias Fischer, Arno Knapitsch, Duncan Zauss, Ethan Weber, Nelson Antunes, Jonathon Luiten, Manuel Lopez-Antequera, Samuel Rota Bulò, Christian Richardt, Deva Ramanan, Sebastian Scherer, Peter Kontschieder

International Conference on 3D Vision (3DV), 2026

2025

BulletGen: Improving 4D Reconstruction with Bullet-Time Generation

Denys Rozumnyi, Jonathon Luiten, Numair Khan, Johannes Schönberger, Peter Kontschieder

arXiv, 2025

Fixing the RANSAC Stopping Criterion

Johannes Schönberger, Viktor Larsson, Marc Pollefeys

arXiv, 2025

MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion

Zador Pataki, Paul-Edouard Sarlin, Johannes Schönberger, Marc Pollefeys

Conference on Computer Vision and Pattern Recognition (CVPR), 2025

2024

Global Structure-from-Motion Revisited

Linfei Pan, Daniel Barath, Marc Pollefeys, Johannes Schönberger

European Conference on Computer Vision (ECCV), 2024

Robust Incremental Structure-from-Motion with Hybrid Features

Shaohui Liu, Yidan Gao, Tianyi Zhang, Rémi Pautrat, Johannes Schönberger, Viktor Larsson, Marc Pollefeys

European Conference on Computer Vision (ECCV), 2024

2023

A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction

Silvan Weder, Francis Engelmann, Johannes Schönberger, Akihito Seki, Marc Pollefeys, Martin Oswald

arXiv, 2023

2022

LaMAR: Benchmarking Localization and Mapping for Augmented Reality

Paul-Edouard Sarlin, Mihai Dusmanu, Johannes Schönberger, Pablo Speciale, Lukas Gruber, Viktor Larsson, Ondrej Miksik, Marc Pollefeys

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

Lukas Schmid, Jeffrey Delmerico, Johannes Schönberger, Juan Nieto, Marc Pollefeys, Roland Siegwart, Cesar Cadena

International Conference on Robotics and Automation (ICRA), 2022

Privacy Preserving Partial Localization

Marcel Geppert, Viktor Larsson, Johannes Schönberger, Marc Pollefeys

Conference on Computer Vision and Pattern Recognition (CVPR), 2022

2021

Reconstructing and grounding narrated instructional videos in 3D

Dimitri Zhukov, Ignacio Rocco, Ivan Laptev, Josef Sivic, Johannes Schönberger, Bugra Tekin, Marc Pollefeys

arXiv, 2021

Cross-Descriptor Visual Localization and Mapping

Mihai Dusmanu, Ondrej Miksik, Johannes Schönberger, Marc Pollefeys

International Conference on Computer Vision (ICCV), 2021

Privacy Preserving Localization and Mapping from Uncalibrated Cameras

Marcel Geppert, Viktor Larsson, Pablo Speciale, Johannes Schönberger, Marc Pollefeys

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings

Mihai Dusmanu, Johannes Schönberger, Sudipta N. Sinha, Marc Pollefeys

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

NeuralFusion: Online Depth Fusion in Latent Space

Silvan Weder, Johannes Schönberger, Marc Pollefeys, Martin R. Oswald

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

2020

Multi-View Optimization of Local Feature Geometry

Mihai Dusmanu, Johannes Schönberger, Marc Pollefeys

European Conference on Computer Vision (ECCV), 2020

Privacy Preserving Structure-from-Motion

Marcel Geppert, Viktor Larsson, Pablo Speciale, Johannes Schönberger, Marc Pollefeys

European Conference on Computer Vision (ECCV), 2020

RoutedFusion: Learning Real-time Depth Map Fusion

Silvan Weder, Johannes Schönberger, Marc Pollefeys, Martin R. Oswald

Conference on Computer Vision and Pattern Recognition (CVPR), 2020

HoloLens 2 Research Mode as a Tool for Computer Vision Research

Dorin Ungureanu, Federica Bogo, Silvano Galliani, Pooja Sama, Xin Duan, Casey Meekhof, Jan Stühmer, Thomas J. Cashman, Bugra Tekin, Johannes Schönberger, Pawel Olszta, Marc Pollefeys

arXiv, 2020

2019

Privacy Preserving Image Queries for Camera Localization

Pablo Speciale, Johannes Schönberger, Sudipta N. Sinha, Marc Pollefeys

International Conference on Computer Vision (ICCV), 2019

Privacy Preserving Image-Based Localization

Pablo Speciale, Johannes Schönberger, Sing Bing Kang, Sudipta N. Sinha, Marc Pollefeys

Conference on Computer Vision and Pattern Recognition (CVPR), 2019

SciPy 1.0 - Fundamental Algorithms for Scientific Computing in Python

Virtanen, Gommers, Oliphant, SciPy 1.0 Contributors

Nature Methods, 2019

2018

Robust Methods for Accurate and Efficient 3D Modeling from Unstructured Imagery

Johannes Schönberger

PhD Thesis, 2018

Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching

Johannes Schönberger, Sudipta N. Sinha, Marc Pollefeys

European Conference on Computer Vision (ECCV), 2018

Learning Priors for Semantic 3D Reconstruction

Ian Cherabier, Johannes Schönberger, Martin Oswald, Marc Pollefeys, Andreas Geiger

European Conference on Computer Vision (ECCV), 2018

VSO: Visual Semantic Odometry

Nektarios Lianos, Johannes Schönberger, Marc Pollefeys, Torsten Sattler

European Conference on Computer Vision (ECCV), 2018

Semantic Visual Localization

Johannes Schönberger, Marc Pollefeys, Andreas Geiger, Torsten Sattler

Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Augmenting Crowd-Sourced 3D Reconstructions using Semantic Detections

True Price, Johannes Schönberger, Zhen Wei, Marc Pollefeys, Jan-Michael Frahm

Conference on Computer Vision and Pattern Recognition (CVPR), 2018

2017

Comparative Evaluation of Hand-Crafted and Learned Local Features

Johannes Schönberger, Hans Hardmeier, Torsten Sattler, Marc Pollefeys

Conference on Computer Vision and Pattern Recognition (CVPR), 2017

A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos

Thomas Schöps, Johannes Schönberger, Silvano Galliani, Torsten Sattler, Konrad Schindler, Marc Pollefeys, Andreas Geiger

Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Mapping on the Fly: Real-Time 3D Dense Reconstruction, Digital Surface Map and Incremental Orthomosaic Generation for Unmanned Aerial Vehicles

Timo Hinzmann, Johannes Schönberger, Marc Pollefeys, Roland Siegwart

International Conference on Field and Service Robotics (FSR), 2017

2016

A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval

Johannes Schönberger, True Price, Torsten Sattler, Jan-Michael Frahm, Marc Pollefeys

Asian Conference on Computer Vision (ACCV), 2016

Pixelwise View Selection for Unstructured Multi-View Stereo

Johannes Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm

European Conference on Computer Vision (ECCV), 2016

Indoor-Outdoor 3D Reconstruction Alignment

Andrea Cohen, Johannes Schönberger, Pablo Speciale, Torsten Sattler, Jan-Michael Frahm, Marc Pollefeys

European Conference on Computer Vision (ECCV), 2016

Structure-from-Motion Revisited

Johannes Schönberger, Jan-Michael Frahm

Conference on Computer Vision and Pattern Recognition (CVPR), 2016

From Dusk till Dawn: Modeling in the Dark

Filip Radenovic, Johannes Schönberger, Dinhuang Ji, Jan-Michael Frahm, Ondrej Chum, Jiri Matas

Conference on Computer Vision and Pattern Recognition (CVPR), 2016

2015

Efficient Two-View Geometry Classification

Johannes Schönberger, Alexander C. Berg, Jan-Michael Frahm

German Conference on Pattern Recognition (GCPR), 2015

PAIGE: PAirwise Image Geometry Encoding for Improved Efficiency in Structure-from-Motion

Johannes Schönberger, Alexander C. Berg, Jan-Michael Frahm

Conference on Computer Vision and Pattern Recognition (CVPR), 2015

From Single Image Query to Detailed 3D Reconstruction

Johannes Schönberger, Filip Radenovic, Ondrej Chum, Jan-Michael Frahm

Conference on Computer Vision and Pattern Recognition (CVPR), 2015

Reconstructing the World* in Six Days *(As Captured by the Yahoo 100 Million Image Dataset)

Jared Heinly, Johannes Schönberger, Enrique Dunn, Jan-Michael Frahm

Conference on Computer Vision and Pattern Recognition (CVPR), 2015

2014

scikit-image: Image processing in Python

Stéfan van der Walt, Johannes Schönberger, Juan Nunez-Iglesias, François Boulogne, Joshua D. Warner, Neil Yager, Emmanuelle Gouillart, Tony Yu, scikit-image contributors

PeerJ, 2014

Structure-from-motion for MAV image sequence analysis with photogrammetric applications

Johannes Schönberger, Friedrich Fraundorfer, Jan-Michael Frahm

Photogrammetric Computer Vision Symposium (PCV), 2014

Benefit of Using Multiple Baselines and Multiple Aspects for SAR Interferometry of Urban Areas

Michael Schmitt, Johannes Schönberger, Uwe Stilla

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2014

Adaptive Covariance Matrix Estimation for Multi-Baseline InSAR Data Stacks

Michael Schmitt, Johannes Schönberger, Uwe Stilla

IEEE Transactions on Geoscience and Remote Sensing (TGARS), 2014

2013

Potential of Airborne Single-Pass Millimeterwave InSAR Data for Individual Tree Recognition

Michael Schmitt, Alex Brück, Johannes Schönberger, Uwe Stilla

33. Wissenschaftlich Technische Jahrestagung der DGPF, 2013

Miscellaneous

Patents

Matching Between 2D And 3D For Direct Localization Johannes Schönberger, Rui Wang, Prune Truong, Marc Pollefeys US Patent App. 18/055,722, 2024
Access Authentication Using Obfuscated Biometrics Johannes Schönberger, Marc Pollefeys US Patent App. 17/997,081, 2023
Collecting Telemetry Data for 3D Map Updates Johannes Schönberger, Marc Pollefeys US Patent App. 17/751,193, 2023
Updating a 3D Map of an Environment Christoph Vogel, Jan-Willem Buurlage, Johannes Schönberger, Juan Nieto, Marc Pollefeys, Timon Knigge, Marcel Geppert US Patent App. 17/743,430, 2023
Facade Biasing for Reflection Correction in Photogrammetric Reconstruction Michael Jones, Johannes Schönberger WO 2023 023266 A1, 2023
Image-based Localization Johannes Schönberger, Marc Pollefeys US Patent 11,145,083, 2021
Fusing Disparity Proposals in Stereo Matching Sudipta Sinha, Marc Pollefeys, Johannes Schönberger US Patent 10,878,590, 2020
Methods, Systems, and Computer Readable Media for Image Overlap Detection Jared Heinly, Johannes Schönberger, Enrique Dunn, Jan-Michael Frahm US Patent 10,504,000, 2018

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”
CVPR 2019/2020, ECCV 2020, Co-organizer, “Long-Term Visual Localization Benchmark”
ECCV 2020, Co-organizer, “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”