Compression Performances of Computer Vision Based Coding

This paper presents new results in the field of very low bitrate coding and compression using 3D informations. Contrary to prior art in model-based coding where 3D models have to be known, the 3D models are automatically computed from the original video sequence. The camera parameters and the scene content are supposed unknown and the video sequence is processed on the fly. A stream of 3D models is then extracted and compressed, using adapted compression techniques. We finally show the results of the proposed compression scheme, and the efficiency of this approach.