Paul Streli
PhD student, Department of Computer Science, ETH Zürich
I am a PhD student at the Sensing, Interaction & Perception Lab at ETH Zürich with Christian Holz, supported by a Meta Research PhD Fellowship. My research is on computational interaction, human motion estimation, and applications in emerging Mixed Reality systems. Combining my background in machine learning, computer vision and signal processing, I develop learning-based perception algorithms that infer natural and precise user input and motions from passive sensor observations.
Before starting my PhD, I completed a master’s degree in Electrical & Electronic Engineering at Imperial College London. I worked as a
Research Scientist intern at Meta Reality Labs and an AI research intern at TikTok.
Please reach out via email if you want to know more about my work.
CV / Google Scholar / Github / LinkedIn / X (Twitter)
publications
- MANIKIN: Biomechanically Accurate Neural Inverse Kinematics for Human Motion EstimationIn Proceedings of the European Conference on Computer Vision (ECCV). 2024.
- EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations EverywhereIn Proceedings of the European Conference on Computer Vision (ECCV). 2024.
- TapID: Rapid Touch Interaction in Virtual Reality using Wearable SensingIn 2021 IEEE Virtual Reality and 3D User Interfaces (VR). 2021. (Accompanying demo received best demonstration award (juried)).