Speaker: Professor Lourdes Agapito, UCL-CS
UCL Contact: Licia Capra (Visitors from outside UCL please email in advance).
Date/Time: 23 Jan 19, 13:00 - 14:00
Venue: Roberts G06
The talk will be preceded 12:15pm-1pm by drinks and nibbles in the foyer of MPEB 5th floor.
As humans we take the ability to perceive the dynamic world around us in three dimensions for granted. From an early age we can grasp an object by adapting our fingers to its 3D shape; we can understand our mother's feelings by interpreting her facial expressions; or we can effortlessly navigate through a busy street. All of these tasks require some internal 3D representation of shape, deformations and motion.
Building algorithms that can emulate this level of human 3D perception has proved to be a much harder task than initially anticipated. While some degree of success has been achieved when the scene observed by a camera is static or "rigid", inferring the 3D geometry of the vivid moving real world is still in its infancy. This challenge has fascinated me throughout my research career.
In this lecture I will show progress from our early systems which captured sparse 3D models with primitive representations of deformation towards our most recent algorithms which can capture human motion or every fold and detail of faces and clothes in 3D using as input video sequences taken with a single consumer camera. There is now great short-term potential for commercial uptake of this technology, and I will show applications to robotics, visual effects for the film industry and synthetic media.
Professor Lourdes Agapito
Professor Lourdes Agapito obtained her BSc, MSc and PhD degrees from the Universidad Complutense de Madrid (Spain). She held an EU Marie Curie Postdoctoral Fellowship at The University of Oxford's Robotics Research Group before being appointed as a Lecturer at Queen Mary, University of London in 2001. In 2008 she was awarded an ERC Starting Grant to carry out research on the estimation of 3D models of non-rigid surfaces from monocular video sequences. In July 2013 she joined UCL Computer Science where she leads a research team as Professor of 3D Vision that focuses on 3D dynamic scene understanding from video.
Lourdes was Program Chair for CVPR 2016, the top annual conference in computer vision; in addition she was Programme Chair for 3DV'14 and serves regularly as Area Chair for all the main computer vision conferences. She was keynote speaker for ICRA, the top robotics conference, in 2017 and CVMP in 2015. Lourdes is Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), the International Journal of Computer Vision (IJCV) a member of the Executive Committee of the British Machine Vision Association and of the EPSRC Peer Review College. In 2017 she co-founded Synthesia, a London based startup that innovates at the intersection of vision, graphics and deep learning to achieve photo-realistic video synthesis.