Tobias Fischer

Tobias Fischer

Ph.D. Student in Computer Vision

ETH Zürich

Biography

I’m a Ph.D. student at the Computer Vision and Geometry Group of ETH Zürich working with Prof. Marc Pollefeys and Dr. Peter Kontschieder at Meta Reality Labs Zurich. I obtained my M.Sc. and B.Sc. degrees in Computer Science from RWTH Aachen University, where I worked with Dr. Jonathon Luiten and Prof. Bastian Leibe as a student research assistant. In 2020, I worked on a remote research project with Prof. Trevor Darrell at the University of California, Berkeley. My research focuses on reconstruction, rendering, and understanding of dynamic scenes.

Interests

  • Computer Vision
  • Neural Rendering
  • Dynamic Scene Understanding

Education

  • Ph.D. Computer Science, 2020 - now

    ETH Zürich

  • M.Sc. Computer Science, 2016 - 2020

    RWTH Aachen University

  • B.Sc. Computer Science, 2013 - 2016

    RWTH Aachen University

Selected Publications

Dynamic 3D Gaussian Fields for Urban Areas

Tobias Fischer, Jonas Kulhanek, Samuel Rota Bulò, Lorenzo Porzi, Marc Pollefeys, Peter Kontschieder
Dynamic 3D Gaussian Fields for Urban Areas

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

Tobias Fischer, Lorenzo Porzi, Samuel Rota Bulò, Marc Pollefeys, Peter Kontschieder
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Multi-Level Neural Scene Graphs for Dynamic Urban Environments

R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras

Aron Schmied*Equal Contribution, Tobias Fischer*Equal Contribution, Martin Danelljan, Marc Pollefeys, Fisher Yu
International Conference on Computer Vision (ICCV), 2023
R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras

QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking

Tobias Fischer*Equal Contribution, Thomas E Huang*Equal Contribution, Jiangmiao Pang*Equal Contribution, Linlu Qiu, Haofeng Chen, Trevor Darrell, Fisher Yu
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking

OVTrack: Open-Vocabulary Multiple Object Tracking

Siyuan Li*Equal Contribution, Tobias Fischer*Equal Contribution, Lei Ke, Henghui Ding, Martin Danelljan, Fisher Yu
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
OVTrack: Open-Vocabulary Multiple Object Tracking

CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion

Tobias Fischer*Equal Contribution, Yung-Hsu Yang*Equal Contribution, Suryansh Kumar, Min Sun, Fisher Yu
Conference on Robot Learning (CoRL), 2022
CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion

Monocular Quasi-Dense 3D Object Tracking

Hou-Ning Hu, Yung-Hsu Yang, Tobias Fischer, Trevor Darrell, Fisher Yu, Min Sun
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
Monocular Quasi-Dense 3D Object Tracking

Track to Reconstruct and Reconstruct to Track

Jonathon Luiten*Equal Contribution, Tobias Fischer*Equal Contribution, Bastian Leibe
IEEE Robotics and Automation Letters (RA-L), 2020
Track to Reconstruct and Reconstruct to Track

Experience

 
 
 
 
 

Research Scientist Intern

Meta Reality Labs

Jun 2024 – Dec 2024 Zurich, Switzerland
Research project on neural rendering.
 
 
 
 
 

Visiting Researcher (Remote)

BAIR Lab, University of California, Berkeley

Jun 2020 – Nov 2020 CA, USA
Research project on 3D Multi-Object Tracking. Remote due to COVID-19 pandemic.
 
 
 
 
 

Research Intern

ZF Group

Mar 2020 – May 2020 Friedrichshafen, Germany
Enhanced the performance of the LiDAR 3D Object Detection model by optimizing architecture, training scheme and data sampling / augmentation.
 
 
 
 
 

Student Research Assistant

Visual Computing Institute, RWTH Aachen University

Oct 2018 – Feb 2020 Aachen, Germany
Research on 3D Scene Understanding including a journal publication on Multi-Object Tracking and Top 4% placement in a Kaggle challenge on 3D object detection. Includes master thesis.

Projects and Activities

 
 
 
 
 

Software Engineer Driverless

EcurieAix, Formula Student Team RWTH Aachen e.V.

Nov 2018 – Sep 2019
Increased the performance of the perception system by 105% and efficiency by 200% by optimizing architecture, training scheme and accelerating inference via TensorRT. 3rd at FS Italy, 7th at FS Germany competitions. Watch the car presentation here.
 
 
 
 
 

UNITECH International Programme

UNITECH International

Aug 2017 – Sep 2018

Unique management and soft skill development for STEM students:

  • Academic Exchange at Trinity College Dublin
  • Internship abroad at KOSTAL Electrica SA, Barcelona
  • Team Building Workshop, INSA Lyon
  • Business Case Study, Politecnico di Milano
  • Closing Week, Chalmers University
  • Professional Coaching

Awards

STEM Award IT

audimax Medien GmbH Oct 2020
1st Prize for an outstanding master thesis in the STEM field. Watch the winner interviews here.

Porsche IT Scholarship

Dr. Ing. h.c. F. Porsche AG Oct 2018 – Sep 2019
Scholarship for excellent IT students issued for the period of one year.

Academic Service

  • Reviewer: NeurIPS, ICCV, ECCV, CVPR, ICRA, IROS, RA-L
  • Workshop Organizer: CVPR'21
  • Challenge Host: CVPR'21, CVPR'22, ECCV'22, CVPR'23

Contact