Region Motion-based Adaptive Composite Long-Term Reference Coding for VVC

The adoption of composite long-term reference (CLTR) in versatile video coding (VVC) has demonstrated good performance, especially for the coding of video containing a large amount of stationary background areas. However, if the long-term reference (LTR) picture is constructed by using the frames that contain lots of foreground contents, the composed LTR picture cannot offer enough background information for the coding of target frame. To effectively apply CLTR to video coding, especially to VVC, we propose a region motion-based determination method to adaptively choose long-term and short-term reference pictures for inter-picture coding. The experimental results demonstrate that our proposed method can achieve promising performance improvement compared with the results generated from VVC common test condition and the traditional LTR-based coding scheme.