Joint Learned and Traditional Video Compression for P Frame(CVPR 2020 Workshops)

1. A decoder-side template-based inter prediction method, an efficient way to obtain reference blocks without the need to signal the motion vectors.
2. A CNN post filter is proposed to suppress visual artifacts and improve the decoded image quality.
3. An advanced SSIM based rate-distortion optimization model is proposed to achieve best balance between the coding bits and the decoded image quality.