Decoder-side Cross Resolution Synthesis for Video Compression Enhancement

1 Dec 2020  ·  Ming Lu, Tong Chen, zhenyu Dai, Dong Wang, Dandan Ding, Zhan Ma ·

This paper proposes a decoder-side Cross Resolution Synthesis (CRS) module to pursue better compression efficiency beyond the latest Versatile Video Coding (VVC), where we encode intra frames at original high resolution (HR), compress inter frames at a lower resolution (LR), and then super-resolve decoded LR inter frames with the help from preceding HR intra and neighboring LR inter frames. For a LR inter frame, a motion alignment and aggregation network (MAN) is devised to produce temporally aggregated motion representation (AMR) for the guarantee of temporal smoothness; Another texture compensation network (TCN) inputs decoded HR intra frame, re-sampled HR intra frame, and this LR inter frame to generate multiscale affinity map (MAM) and multiscale texture representation (MTR) for better augmenting spatial details; Finally, similarity-driven fusion synthesizes AMR, MTR, MAM to upscale LR inter frame for the removal of compression and resolution re-sampling noises... We enhance the VVC using proposed CRS, showing averaged 8.76% and 11.93% Bj{\o}ntegaard Delta Rate (BD-Rate) gains against the latest VVC anchor in Random Access (RA) and Low-delay P (LDP) settings respectively. In addition, experimental comparisons to the state-of-the-art super-resolution (SR) based VVC enhancement methods, and ablation studies are conducted to further report superior efficiency and generalization of proposed algorithm. All materials will be made to public at https://njuvision.github.io/CRS for reproducible research. read more

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here