Aaron Tognoli, a PhD student in Information Technology at the Department of Electronics, Information and Bioengineering of Politecnico di Milano, has received the Honourable Mention Full Paper Award at ETRA 2026 – ACM Symposium on Eye Tracking Research & Applications for the paper “Overcoming Data Scarcity for Event-Based Pupil Tracking with Synthetic and Unlabeled Data”.
The paper, written with Andrea Simpsi, Andrea Aspesi, Marco Cannici, Luca Merigo, Matteo Matteucci and Simone Mentasti, explores how to make pupil tracking more accurate and efficient in wearable devices, such as smart glasses, which need to understand where a person is looking in order to provide more natural and personalized interactions.
The main challenge is that collecting and annotating real-world data is difficult and time-consuming, especially when using event cameras, sensors that record changes in brightness rather than standard video frames. To address this issue, the work proposes combining synthetic data generated in simulation, unlabelled real recordings and a small amount of labelled real data.
This strategy allows models to learn from many controlled examples while also adapting better to real-world conditions. The result is a more practical method for achieving reliable pupil tracking even when only limited annotated data is available.