Our mission is to realize indistinguishable virtual reality contents from the perspectives of fundamental research core techniques in light field acquisition, storage, processing, rendering and display. We explore light field VR technologies ranging from micro scales to macro scales in order to take the lead in the capture, processing and tele-presence of 360-degree 3D dynamic real scenes up to the human-eye resolution.
Our vision is to offer a cross-scale, cross-disciplinary, universal technical platform to facilitate and upgrade other research and application areas, e.g. biomedicine, cultural heritage, digital city, new media, space technologies. VRVC will serve as a pillar of ShanghaiTech's path to a top-notch research institute in the world and become a world-class research center in the correlated areas. We constantly devote ourselves to improving and developing the living conditions, economic development and scientific research in China.
Recent
Publications
No content yet...
Research
Highlights
Computational Cameras and Projectors
Camera models are fundamental to computer vision and graphics. The classical pinhole camera model has long served as the workhorse of 3D imaging applications. Our research aims to develop new imaging systems and algorithms beyond pinhole optics to more effectively acquire, represent, analyze, and utilize the 3D imagery data.
Light Field Imaging for Vision and Graphics
Light fields are image-based representations of scenes. While the original goal of acquiring a light field is to conduct image-based modeling and rendering, our focus has been to apply light field imaging in various applications in computer vision and robotics.
Recovering “Invisible” Objects
Faithfully acquiring invisible or transparent objects such as 3D fluid wavefronts or gas density can greatly benefit fluid mechanics, oceanography, and computer animation. Our focus is to develop non-intrusive solutions by coupling computational cameras with new computer vision algorithms.
Biomedical Imaging and Bioinformatics
Our computational camera work also finds it uses in biomedical imaging and bioinformatics. In the field of bioinformatics, our focus is to apply visual analytics techniques to systematically tackle gene functions and complex regulatory processes.
Privacy-Preserving Surveillance
Video surveillance in public spaces has increased dramatically in recent history. So has concern about the potential for abuse and the general loss of privacy. We explore new solutions on the acquisition front: we aim to design computational cameras that will produce features that are recognizable at the category level but not at the object level.