Seonwook Park

Seonwook Park

PhD student
Advanced Interactive Technologies Lab, ETH Zürich

+41 44 632 79 91
Universitätstrasse 6, 8092 Zürich, Switzerland
ETH Zurich, Department of Computer Science, CNB, H 102


After a bachelor in Physics at Imperial College London, I moved to Switzerland to study Computational Science and Engineering at ETH Zurich. The flexibility of the master programme allowed me to specialise in robotics and delve into the field of computer vision. In the latter part of my master, I worked with the Computer Vision and Geometry Group on direct visual odometry. I originally come from Seoul, a small town in the Republic of Korea.

I now have the privilege of being supervised by Prof. Dr. Otmar Hilliges in exploring technical human-computer interaction (HCI). My current research interests include appearance-based eye gaze estimation (eye tracking) and closed-loop user preference learning. If you have interesting ideas and would like to work with me, do say hello.




Deep Pictorial Gaze Estimation

AuthorsS. Park, A. Spurr, O. Hilliges
In ProceedingsEuropean Conference on Computer Vision (ECCV), Munich, Germany, 2018


Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings

AuthorsS. Park, X. Zhang, A. Bulling, O. Hilliges
In ProceedingsACM Symposium on Eye Tracking Research and Applications (ETRA), Warsaw, Poland, 2018

Best Presentation Award


Cross-modal Deep Variational Hand Pose Estimation

AuthorsA. Spurr, J. Song, S. Park, O. Hilliges
In ProceedingsCVPR, Salt Lake City, USA, 2018

Accepted as Spotlight Presentation


AdaM: Adapting Multi-User Interfaces for Collaborative Environments in Real-Time

AuthorsS. Park, C. Gebhardt*, R. Rädle*, A. Feit, H. Vrzakova, N. Dayama, H. Yeo, C. Klokmose, A. Quigley, A. Oulasvirta, O. Hilliges
In ProceedingsSIGCHI Conference on Human Factors in Computing Systems, Montréal, Canada, 2018
* These two authors contributed equally to this work.


Illumination Change Robustness in Direct Visual SLAM

AuthorsS. Park, T. Schöps, M. Pollefeys
In ProceedingsIEEE International Conference on Robotics and Automation (ICRA), Singapore, May 2017


Student Theses

SA Spyridon Angelopoulos Can we use Super-Resolution to improve appearance-based gaze estimation?