Encoding and reconstruction of multiview video objects

The authors discuss how disparity-based processing can be used both for compression of multiview video data, and generation of arbitrary viewpoints from the available information of multiple cameras in the context of the MPEG-4 multimedia standard. The examples and results presented here show that viewpoint adaptation toward video objects can be accomplished with low-complexity schemes such as disparity-compensated projection, while high-quality results are presented. The ability to process multiview video is another example of the high flexibility of the MPEG-4 standard, which we expect to be applicable to various new challenging services in the multimedia market