His current research focuses on language driven 3D perception problems within the scope of social perception, in specific, on referral based indoor 3D panoptic segmentation.
Before joining TRACE in 2022, Ozan worked on data efficient LiDAR semantic segmentation for autonomous driving, developing both weakly- and semi-supervised methods to reduce the annotation burden. Before starting his PhD, Ozan received a BSc and MSc from the Department of Electrical Engineering and Information Technology at ETH Zurich.