
Marco Pesavento
Academic and research departments
Centre for Vision, Speech and Signal Processing (CVSSP), Department of Electrical and Electronic Engineering.About
My research project
Super-resolution 4D reconstruction of peopleThis PhD will address the challenge of learning animated representations of people for highly realistic rendering in interactive augmented reality applications. Novel representations exploiting deep learning of both shape and appearance will be investigated. The texture space domain, together with online 4D alignment, will be investigated to give compact representation of dynamic shape detail. A framework to allow high-level interactive control of the animation exploiting the learnt representation will be developed. This approach has potential for impact in content production for both traditional media film/games/TV and new forms of immersive augmented and virtual reality experience.
Supervisors
This PhD will address the challenge of learning animated representations of people for highly realistic rendering in interactive augmented reality applications. Novel representations exploiting deep learning of both shape and appearance will be investigated. The texture space domain, together with online 4D alignment, will be investigated to give compact representation of dynamic shape detail. A framework to allow high-level interactive control of the animation exploiting the learnt representation will be developed. This approach has potential for impact in content production for both traditional media film/games/TV and new forms of immersive augmented and virtual reality experience.