| Research Mission: |
Creating high-quality and realistic virtual content is nowadays an important task for modern virtual worldsMe games and movies. While it is possible to roughly capture the motion and static shape of performers and scenes, capturing subtle surface motion details and appearance of actors (such as muscle bulging, cloth motion or facial wrinkles) and details of real scenes (such as moving leaves on trees) is still a challenging problem. The group focuses on researching novel techniques for capturing and processing highly detailed models of performers and scenes in motion using optical methods. Recent years have seen remarkable advances in the field, and so called performance capture methods have been developed that are able to capture motion, coherent geometry and appearance from a sparse set of input videos. However, many algorithms to date still do not produce results on a quality level that would be necessary to apply them in production environments. Achieving high-quality reconstructions that satisfy the requirements of these environments with as little human interaction as possible provide a whole new set of research challenges. In our work we plan to develop new methods for simultaneous motion, geometry and appearance acquisition that bring us closer to the goal of reconstructing completely realistic virtual performances and scenes. |
