A Non-Conventional Approach to the Conversion of 2D Video and Film Content to Stereoscopic 3D

We will present a non-conventional approach and method for converting naturalistic (non-computer-generated) 2D video and film material to Stereoscopic 3D. We will present experimental evidence to show the efficacy of colour-based surrogate depth maps for automatic 2D-to-3D conversion aimed at small screen applications. We will then present a semi-automatic 2D-to-3D conversion system (CRC-DMEG), also based on surrogate depth maps, for the conversion of video and film contents for commercial projection on large cinema screens. A major advantage of CRC-DMEG is that it exploits the correlation between the 2D colour images and the surrogate depth maps to allow for direct manipulation of the depth of objects in a scene. Another major advantage is that it allows for the instant realization of depth details, such as raindrops, foliage and the textures found in carpets. Our approach and method, minimizes the labor-intensive work associated with the conventional method of rotoscoping. Moreover, the manual task of filling in disoccluded regions is also significantly reduced.