Research Overview

Welcome to the AIT Lab where AI meets Interactive Technologies. We do research at the intersection of Machine Learning, Computer Vision and Human Computer Interaction (HCI). Our main mission is to develop new ways for humans to interact with complex interactive systems (computers, wearables, robots), powered by advanced algorithms and technologies in machine perception, planning and data driven user modelling. Please see research and publications for more information.

The AIT Lab, led by Prof. Dr. Otmar Hilliges, is within the Department of Computer Science at ETH Zurich. The group is jointly affiliated with the Institute of Visual Computing and Institute of Pervasive Computing.

Latest News

19.02.2018
Our paper on 3D hand pose estimation from monocular RGB images is accepted as spotlight at CVPR'18.
09.02.2018
Our paper on digital ink synthesis wins Best Paper Honorable Mention Award at CHI'18.
24.10.2018
Our paper on haptics for AR/VR wins Best Paper Honorable Mention Award at UIST'17.
11.12.2017
Two papers accepted at ACM SIGCHI.
12.10.2017
Our paper on human motion models wins Best Paper Award at 3DV '17
01.08.2017
One paper accepted at ACM UIST 2017.
30.03.2017
Two papers accepted at ACM SIGGRAPH and IEEE CVPR.
18.01.2017
Journal paper accepted for IEEE Robotics & Automation Letters (RA-L).
15.12.2016
Otmar Hilliges receives an ERC starting grant.

Open PostDoc positions

We are currently looking for 2 post-docs with a background in either i) machine learning, bayesian optimisation, active learning, variational methods, deep-learning or related areas or ii) computer vision, graphics, robotics, numerical methods or physical simulation.

Excellent programming skills in C++ or other high-level language are expected and experience in Matlab, Python, OpenGL, or CUDA are beneficial. Fluent communication skills (written and presentation) in English are essential.

Positions are fully funded (via ERC starting grant) and are available to those of any nationality (some knowledge of German is beneficial but not essential). For more details see how to apply.


Latest Projects


Teaser-Picture

Optimizing for Aesthetically Pleasing Quadrotor Camera Motion

AuthorsC. Gebhardt, S. Stevsic, O. Hilliges
In ProceedingsACM Transactions on Graphics (Proceedings of ACM SIGGRAPH) (Volume: 37, Issue: 4), August 2018

Teaser-Picture

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

Teaser-Picture

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

Teaser-Picture

DeepWriting: Making Digital Ink Editable via Deep Generative Modeling

AuthorsE. Aksan, F. Pece, O. Hilliges
In ProceedingsSIGCHI Conference on Human Factors in Computing Systems, Montréal, Canada, 2018

Honorable Mention Best Paper Award

Teaser-Picture

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.

Teaser-Picture

Learning Human Motion Models for Long-term Predictions

AuthorsP. Ghosh, J. Song, E. Aksan, O. Hilliges
In Proceedings3D Vision (3DV), 2017 International Conference on, 2017

Best Paper Award

Teaser-Picture

MagTics: Flexible and Thin Form Factor Magnetic Actuators for Dynamic and Wearable Haptic Feedback

AuthorsF. Pece*, J. Zarate*, V. Vechev, N. Besse, O. Gudozhnik, H. Shea, O. Hilliges
In ProceedingsACM Symposium on User Interface Software and Technologies (UIST), Quebec City, Canada, Oct 2017
* These two authors contributed equally to this work.

Honorable Mention Best Paper Award

Teaser-Picture

Real-time Planning for Automated Multi-View Drone Cinematography

AuthorsT. Nägeli, L. Meier, A. Domahidi, J. Alonso-Mora, O. Hilliges
In ProceedingsACM Transactions on Graphics (Proceedings of ACM SIGGRAPH), Los Angeles, USA, 2017

Teaser-Picture

Guiding InfoGAN with Semi-Supervision

AuthorsA. Spurr, E. Aksan, O. Hilliges
In ProceedingsECML PKDD, Skopje, Macedonia, 2017

Teaser-Picture

Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

AuthorsJ. Song, L. Wang, L. Van Gool, O. Hilliges
In ProceedingsCVPR, Hawaii, USA, 2017

Accepted as oral presentation

Teaser-Picture

Real-time Motion Planning for Aerial Videography with Dynamic Obstacle Avoidance and Viewpoint Optimization

AuthorsT. Nägeli, J. Alonso-Mora, A. Domahidi, D. Rus, O. Hilliges
In ProceedingsIEEE Robotics and Automation Letters (Volume: 2, Issue: 3), July 2017

Teaser-Picture

Interacting with Soli: Exploring Fine-Grained Dynamic Gesture Recognition in the Radio-Frequency Spectrum

AuthorsS. Wang*, J. Song*, J. Lien, I. Poupyrev, O. Hilliges
In ProceedingsACM Symposium on User Interface Software and Technologies (UIST), Tokyo, Japan, Oct 2016
* These two authors contributed equally to this work.

Teaser-Picture

Rig Animation with a Tangible and Modular Input Device

AuthorsO. Glauser, W. Ma, D. Panozzo, A. Jacobson, O. Hilliges, O. Sorkine-Hornung
In ProceedingsACM Transactions on Graphics (Proceedings of ACM SIGGRAPH), Anaheim, CA, USA, Jul 2016

Teaser-Picture

Airways: Optimization-based Planning of Quadrotor Trajectories according to High-Level User Goals

AuthorsC. Gebhardt*, B. Hepp*, T. Nägeli, S. Stevsic, O. Hilliges
In ProceedingsSIGCHI Conference on Human Factors in Computing Systems, San Jose, CA, 2016
* These two authors contributed equally to this work.

Teaser-Picture

DefSense: Computational Design of Customized Deformable Input Devices

AuthorsM. Bächer, B. Hepp*, F. Pece*, P. Kry, B. Bickel, B. Thomaszewski, O. Hilliges
In ProceedingsSIGCHI Conference on Human Factors in Computing Systems, San Jose, CA, 2016
* These two authors contributed equally to this work.

Teaser-Picture

Two-Stream SR-CNNs for Action Recognition in Videos

AuthorsY. Wang, J. Song, L. Wang, L. Van Gool, O. Hilliges
In ProceedingsBritish Machine Vision Conference (BMVC), York, UK, 2016

Teaser-Picture

Duo-VIO: Fast, Light-weight, Stereo Inertial Odometry

AuthorsN. de Palezieux, T. Nägeli, O. Hilliges
In ProceedingsIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, South Korea, Oct 2016

Teaser-Picture

Omni-directional person tracking on a flying robot using occlusion-robust ultra-wideband signals

AuthorsB. Hepp*, T. Nägeli*, O. Hilliges
In ProceedingsIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, South Korea, Oct 2016
* These two authors contributed equally to this work.