ETH Zurich - D-INFK - IVC - CVG - People - PhD Students

PhD Students


Peidong Liu 刘沛东

ETH Zürich
Universitätstrasse 6
CH-8092 Zürich

Department of Computer Science
Computer Vision and Geometry Group
CAB G 84.2

+41 (0)44 63 39 386


  • Feb 2020: our paper on "Deep shutter unrolling network" is accepted by CVPR 2020 in Seattle. We thank the area chairs and the anonymous reviewers for their recommendations.
  • Jan 2020: our paper on "Self-supervised motion deblurring" is accepted by the Robotics and Automation Letters (RA-L), in conjunction with ICRA 2020 in Paris, France. We thank both the editors and the anonymous reviewers for their recommendations and valuable suggestions to further improve our paper.
  • Feb 2019: we have two papers got accepted by ICRA 2019 in Montreal, Canada.
  • Sep 2018: we have two papers on "autonomous driving" available on arXiv.
  • June 2018: our paper "Towards robust visual odometry with a multi-camera system" is accepted by IROS 2018 in Madrid, Spain.
  • Jan 2018: our paper "Robust dense mapping for large-scale dynamic environments" is accepted by ICRA 2018 in Brisbane, Australia.
  • June 2017: our paper "Direct visual odometry for a fisheye stereo camera" is accepted by IROS 2017 in Vancouver, BC, Canada.

About Me

I'm a PhD student from the Computer Vision and Geometry Group, ETH Zürich. My supervisor is Prof. Marc Pollefeys. I also work closely with Prof. Dr. Andreas Geiger, Dr. Torsten Sattler and Dr. Lionel Heng.

Prior joining CVG in September 2015, I was part of the Unmanned Systems Research Group from the National University of Singapore (NUS), where I obtained both my master and bachelor degrees in Electrical Engineering.

Reseach Interests

I am interested in developing novel visual perception algorithms for mobile robots. In particular, my current research mainly focuses on developing robust visual localization and mapping algorithms to help mobile robots know where they are and what surround them.

If you are interested in my research, you are mostly welcome to do your master or semester project with me!

Finished Master Theses

  • Andrei Barsan, "Robust Dense Mapping for Large-Scale Dynamic Environments", Feb 2017 - Aug 2017, now PhD student in University of Toronto
  • Xinyuan Yu, "Stereo Camera Based Large-Scale Semantic Mapping", Dec 2016 - Jun 2017, now Research Intern in Robotic Institute, Carnegie Mellon University
  • Kailin Huang, "Dense Object SLAM", Apr 2018 - Oct 2018


You can find more details from my google scholar page.
  1. P. Liu, Z. Cui, V. Larsson and M. Pollefeys, "Deep shutter unrolling network", Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 2020. [Paper] [Supp] [Code]
  2. P. Liu, J. Janai, M. Pollefeys, T. Sattler and A. Geiger, "Self-supervised motion deblurring", Robotics and Automation Letters (RA-L), in conjunction with ICRA, Paris, France, 2020. [Paper] [Supp] [Code] [Blog]
  3. L. Heng, B. Choi, Z. Cui, M. Geppert, S. Hu, B. Kuan, P. Liu, R. Nguyen, Y.C. Yeo, A. Geiger, G.H. Lee, M. Pollefeys and T. Sattler, "Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System", arXiv:1809.05477, 2018; ICRA 2019. [Paper]
  4. M. Geppert, P. Liu, Z. Cui, M. Pollefeys and T. Sattler, "Efficient 2D-3D Matching for Multi-Camera Visual Localization", arXiv:1809.06445, 2018. ICRA 2019. [Paper]
  5. P. Liu, M. Geppert, L. Heng, T. Sattler, A. Geiger and M. Pollefeys, "Towards Robust Visual Odometry with a Multi-Camera System", IROS, Madrid, Spain, 2018. [Paper][Project Page]
  6. A. Barsan, P. Liu, M. Pollefeys and A. Geiger, "Robust Dense Mapping for Large-Scale Dynamic Environments", ICRA, Brisbane, Australia, 2018. [Paper][Video][Project Page]
  7. P. Liu, L. Heng, T. Sattler, A. Geiger and M. Pollefeys, "Direct Visual Odometry for a Fisheye-Stereo Camera", IROS, Vancouver, Canada, 2017. [Paper][Video]

© CVG, ETH Zürich webmaster: