Photorealistic representation of natural scenes for immersive virtual experience of our world.

Motivated by the advent of mass-market head-mounted immersive displays, we set out to pioneer the technology needed to experience recordings of the real world with the sense of full immersion provided by VR goggles. Achieving this goal requires a concerted effort to address a number of interdisciplinary, closely related challenges in video processing, computer graphics, computer vision, and applied visual perception: Instead of filming a shot from the outside looking in, the action must now be captured and digitally modelled omnidirectionally from within the scene; to facilitate motion parallax and stereoscopic vision during display, authentic views of the recorded scene must be created in real time for arbitrary viewing positions and directions; and to optimise the visual experience of field-of-view immersive displays, perception-aware rendering algorithms must simultaneously take into account the characteristics of our foveal and peripheral vision.
This five-year research project aims to develop the means to experience the recorded real world in full immersion: By importing the real world into immersive displays, we aim to lay the foundations for the way we will watch films in the future, moving away from fixed-point, limited field-of-view screens towards a fully immersive, collective experience.