The aim of this project is to augment traditional 2D-video content with depth using computer vision approaches. To achieve this goal the camera motion and settings will also have to be recovered from the video data. The main application that is envisioned is converting existing 2D-video to 3D-video to provide sufficient content for stereoscopic displays and enable applications such 3D-TV to emerge and flourish. Besides this, the intended research potentially also has important applications in the context of video analysis and compression. Advances in 3D from video will also have a broader impact in areas such as archaeology, cultural heritage, movie special effects, medical, forensics and military reconnaissance applications. The educational impact will not be limited to students directly involved in this project, but will potentially reach many more through tools for video analysis in art schools or educational 3D-videos. We intend to develop a reliable fully automatic approach. Since it will not always be possible to compute the depth from the available image content (e.g. fixed camera), we intend to correctly deal with ambiguities and provide perceptually acceptable results (e.g. fade depth when it can't be computed anymore). Given a 2D video stream, we intend to (1) compute the relative motion between the scene and the camera for each shot, (2) detect independent moving objects and computer their motion and deformation, (3) compute a detailed depth representation for each video.
