SCENE will develop novel scene representations for digital media that go beyond the ability of either sample based (video) or model-based (CGI) methods to create and deliver richer media experiences. The SCENE representation and its associated tools will make it possible to capture 3D video, combine video seamlessly with CGI, manipulate and deliver it to either 2D or 3D platforms in either linear or interactive form. The outcomes will be:• Improved ways of capturing and fusing scene data from multiple cameras and other kinds of sensors, so that structural, depth and surface appearance can be contained in a single representation• A novel scene camera, which can capture appearance and depth to create the necessary input for a scene representation from a single viewpoint• Improved methods for video scene analysis of stereo or multi-view sequences from which to extract spatio-temporally consistent structural information• A video scene representation that goes beyond current image based and computer graphic approaches to obtain an inherently 3D, spatio-temporally consistent worldview• Algorithms and data structures for transforming scene representations into forms that are adapted for efficient storage, distribution and rendering in the context of various application scenarios• Methods of rendering the scene representation at optimal quality for different purposes and receiving platforms, such as postproduction, virtual studios and network delivery to set-top boxes and mobile devices• Methods for merging, editing and manipulating 3D scene information in a re-usable and adaptable manner, supporting interaction, scene modification and object replacement• Media samples that show the use of the technology and representation for digital cinema, virtual studio and network delivery to the home and mobile platforms• An industry-based non-profit SCENE Foundation, to promote the representation and co-ordinate standardisation activities after the end of the project.