Torsten Sattler

I am a senior researcher at the Czech Institute of Informatics, Robotics and Cybernetics (CIIRC) at the Czech Technical University in Prague (CTU), where I am heading the Spatial Intelligence group. My work is in the intersection of 3D computer vision and machine learning, with the goal of making 3D computer vision algorithms such as 3D reconstruction and visual localization more robust and reliable through scene understanding while using 3D computer vision methods to train machine learning models.

Before joining CIIRC in July 2020, I was an associated professor (tenured) in the Department of Electrical Engineering at Chalmers University of Technology. I joined Chalmers in January 2019 after 5 years, first as a PostDoc and then as a senior researcher, in Marc Pollefey's Computer Vision and Geometry Group in the Department of Computer Science at ETH Zurich. Between July 2016 and June 2018, I was Marc's deputy, tasked with the day-to-day operation of the group, during his sabbatical. I obtained a PhD from RWTH Aachen University under the supervision of Leif Kobbelt and Bastian Leibe.

I am an ELLIS scholar and will be a program chair for ECCV 2024.
I am a co-organizer of the 3DGV Seminar series.

Email  /  CV  /  Bio  /  Google Scholar  /  Twitter  /  Github

photo taken by Roman Sejkot
Research

My research interests include (large-scale) image-based localization, real-time localization, 3D mapping and reconstruction, implicit neural scene representations and neural rendering, learning local features, machine learning for 3D computer vision, and camera calibration, with applications in self-driving cars and other autonomous robots as well as augmented and virtual reality. My current work focuses on making algorithms for localization and mapping "smarter" (and thus more robust and reliable) by incorporating higher-level scene understanding into the process.

News

Awards & Recognition

Outstanding Reviewer Awards: CVPR 2021, ICLR 2021, CVPR 2020, ICCV 2019, CVPR 2019, CVPR 2017, ECCV 2016, ICCV 2015, CVPR 2015

PhD Students

Publications

For an up-to-date list of my publications, please see my Google Scholar profile.

Teaching

Lectures

Master Theses
Note: At Chalmers, students can write theses in pairs.

  • 2020:
    Admir Alihodza, Jonas Hejderup: Indoor static 2D map generation and object detection using deep learning and computer vision, academic supervisor and examiner at Chalmers University of Technology for an industrial Master thesis at Volvo
    Philip Anderberg, Fanny Liesén Gullmander: Segmentation of Image Sequences using SuperPixel Sampling Networks, academic supervisor and examiner at Chalmers University of Technology for an industrial Master thesis at Volvo
    Zongshang Pang: Using Stylization to Improve Visual Localization, Chalmers University of Technology
    Ara Jafarzadeh: Localization in Changing Environments: A More Robust Semantic Visual Localization Approach, Chalmers University of Technology
    Celine Back, Ivana Pepic: Simulating medical image data using generative adversarial networks (GANs), academic supervisor and examiner at Chalmers University of Technology for an industrial Master thesis at QRTECH
    Filip Franson, Max Wedenmark: Quality inspection using machine learning techniques for pose estimation, academic supervisor and examiner at Chalmers University of Technology for an industrial Master thesis at Volvo
    Adam Breitholz: Understanding the Limitations of PoseNet, jointly supervised with Laura Leal-Taix\'{e} (TU Munich), Chalmers University of Technology
  • 2019:
    Jonas Garsten, Ivar Wikenstedt: 6DOF camera localization through a short image sequence, Chalmers University of Technology
    Rasmus Lundin, John Wedin: Scalable deep visual localization, jointly supervised with Eric Brachmann (TU Dresden), Chalmers University of Technology
    Earl Fernando Panimayam Fernando: Prioritized 2D-3D Matching for Visual Localization Revisited, Chalmers University of Technology
    Guoxiang Zhou: Visual Semantic Odometry in Dynamic Environments, jointly supervised with Zhaopeng Cui (ETH Zurich), ETH Zurich
    Tomasz Jerzy Firynowicz: Visual localization under challenging conditions, jointly supervised with Zhaopeng Cui (ETH Zurich) and Marcel Geppert (ETH Zurich), ETH Zurich
  • 2018:
    Antoni Rosinol Vidal: Exploiting Regular Structures in SLAM, jointly supervised with Luca Carlone (MIT), MIT
    Qixuan Zhang: Global Structure-from-Motion from Learned Relative Poses, jointly supervised with Johannes L. Schönberger (ETH Zurich), ETH Zurich
  • 2017:
    Qunjie Zhou: Learning Relative Pose Estimation for Visual Localization, jointly supervised with Laura Leal-Taix\'{e} (TU Munich), TU Munich
    Nektarios Lianos: Semantic Simultaneous Localization and Mapping, jointly supervised with Johannes L. Schönberger (ETH Zurich), ETH Zurich
    Krzysztof Lis: Learning Viewpoint Invariant Patches, jointly supervised with Johannes L. Schönberger (ETH Zurich), ETH Zurich
    Benjamin Steger: Building Virtual Scenes from the Real-World for Virtual Reality, jointly supervised with Filip Srajer (ETH Zurich), ETH Zurich
    Marcel Geppert: Simultaneous Localization and Mapping using Generalized Cameras, jointly supervised with Johannes L. Schönberger (ETH Zurich), ETH Zurich
    Andrin Jenal: 3D Tree Net, jointly supervised with Nikolay Savinov (ETH Zurich) and Gaurav Chaurasia (Disney Research Zurich), Disney Research Zurich
  • 2016:
    Hans Hardmeier: Comparison of handcrafted vs. learned feature descriptors for Structure-from-Motion, jointly supervised with Johannes L. Schönberger (ETH Zurich), ETH Zurich
  • 2015:
    Ioannis Marrigis: Incremental and Adaptive 3D Reconstruction in the Large, jointly supervised with Amael Delaunoy (ETH Zurich), ETH Zurich
  • 2014:
    Andreas Haese: 2.5D Capture to Go, RWTH Aachen University
  • 2013:
    Guoyu Lu: Large-scale image-based localization using learnt projection for local features, RWTH Aachen University
    Sven Middelberg: Hybrid Server-Client Image-Based Localization and Tracking for Mobile Devices, at RWTH Aachen University

Bachelor Theses

  • 2017:
    Niklaus Bamert: Efficient Matching Via Hashing for (Close-to) Real-Time Dense 3D Reconstruction, ETH Zurich
  • 2016:
    Luzi Sennhauser: Image-Based Localization using Deep Learning, jointly supervised with Johannes L. Schönberger (ETH Zurich), ETH Zurich
  • 2012:
    Andre Tebart: Augmented Reality Game on Android Tablets, jointly supervised with Dominik Sibbing (RWTH Aachen University), RWTH Aachen University
    Ole Untzelmann: City-Reconstructions by crowdsourcing, RWTH Aachen University
  • 2011:
    Falk Pollok: Real-Time Object Tracking for Augmented Reality on Mobile Devices, RWTH Aachen University
  • 2009:
    Eduard Feicho: Real-Time Feature Extraction and Matching on Mobile Devices, RWTH Aachen University

Semester Theses

  • 2018:
    Niklaus Bamert: Two-stage (semi-)dense real-time 3D depth estimation, ETH Zurich
    Nadja Kämpf: Two-stage (semi-)dense real-time 3D depth estimation, Studies in Mecha- tronics Thesis, ETH Zurich
  • 2017:
    Matteo Ruello: SemanticPaint on HoloLens, co-supervised with Filip Srajer (ETH Zurich), ETH Zurich
  • 2016:
    Nadine Rüegg: Synchronizing Cameras from Motion, ETH Zurich
Commissions of Trust

General Chair:

Program Chair:

  • DAGM GCPR: 2020
  • ECCV: 2024

Area Chair:

  • CVPR: 2018, 2022
  • ECCV: 2020
  • ICCV: 2019, 2021
  • 3DV: 2018, 2019, 2020, 2021
  • ACCV: 2020
  • WACV: 2021

Associate Editor:

  • ICRA: 2019, 2020
  • IEEE RA-L: 2019-

International Program Committee:

  • EuroGraphics: 2020

Workshop Chair:

  • CVPR: 2021

Guest Editor:

  • International Journal of Computer Vision: Special Issue on Performance Evaluation in Computer Vision
  • International Journal of Computer Vision: Special Issue on Traditional Computer Vision in the Age of Deep Learning
  • International Journal of Computer Vision: Special Issue on Computer Vision and Pattern Recognition 2020

This website is based on the source code of Jon Barron's website.
Profile picture taken by Roman Sejkot.