Bio

Michael read a B.Eng at the University of Malta ('05-'09) where he worked on `head orientation estimation' from a monocular camera under Prof. Kenneth P. Camilleri. In the summer of 2009 he moved to France for an internship with the PERCEPTION research team at INRIA Grenoble, under Dr. Miles Hansard and Prof. Radu Horaud. The research undertaken addressed the real-time calibration update of an active binocular camera set-up.

Back in Malta, Michael completed an M.Sc (following awarded Malta-EU scholarship) in mobile robotic vision under the supervision of Prof. Kenneth P. Camilleri ('10-'11). The resulting monocular vision algorithm helped a robot to guide itself without hitting obstacles in a previously unknown environment.

Michael moved to Oxford in 2011 to pursue a doctorate with the Oxford Brookes Vision Group under Dr. Fabio Cuzzolin and Prof. Philip H.S. Torr (following awarded ITS scholarship). His research addressed how a machine may automatically identify particular human actions in huge video databases without location annotation. Michael's dissertation was examined by Prof. Andrew Zisserman and Dr. Tjeerd Olde Scheper. Staying in Oxford, Michael joined the Torr Vision Group at the University of Oxford as a postdoctoral research scientist, where he focused on 'interactive real-time 3D-reconstruction and semantic labeling', human action detection, and object instance segmentation .

In 2017, Michael moved to Mountain View California to create new technologies within the Think Tank Team (Samsung Research America), and later with Samsung Technology and Advanced Research (STAR) Labs, directed by Pranav Mistry.

Currently Michael is developing cutting-edge technology in artificial reality with TWO.