An Intra-Affine Current Picture Referencing Mode for Screen Content Coding in VVC

Abstract

With the rapid development of emerging applications, screen content coding (SCC) is playing a more and more important role. Intra block copy (IBC), as a new tool for SCC, is proved to be efficient when there are many repeating or similar areas within the same picture. However, IBC is based on translational motion model, which may not work well for some blocks with complicated movement content, such as rotation and zoom. In this paper, a new intra-affine current picture referencing mode is proposed. In this new mode, non-translational motion model (affine model) is introduced to intra prediction for SCC to improve coding efficiency. First, candidate set of initial block-affine vectors (BVAffis) is established by a newly designed method. Then, those initial BVAffis are updated through iterative searching algorithm. Moreover, compatibility checking is applied. Compared to VTM3.0, the proposed new mode can achieve 2.53%, 2.47%, and 2.48% BD-rate saving on average for Y, U and V respectively for SCC test sequences. The draft about the new mode (JVET-O0682) was submitted in the 15th JVET meeting.