An application of unified reference picture list for motion-compensated video compression

摘要

Modern video compression standards rely on motion-compensated prediction from multiple reference pictures. In past standardisation efforts following the introduction of bidirectional prediction, reference pictures were typically signalled in two independent lists, used for forward- and backward-prediction. Modern video coding standards, such as H.264/MPEG-4 Advanced Video Coding or High Efficiency Video Coding, extend this concept by removing the separation between preceding and succeeding reference pictures, and allow reference frames to be included in the two lists regardless of their temporal index. Therefore, the principle of using two separate lists can be considered obsolete. This paper evaluates an alternative concept, using a single, unified reference picture list. This alternative list, called “list unified” or LU, reduces reference picture signalling, while all functionalities for motion-compensated prediction using multiple references are preserved. Evaluation shows competitive video coding efficiency compared to the usage of two lists, with the advantage of simplified bitstream parsing and much improved reference picture flexibility.