B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction
This work addresses video quality degradation for users of compression standards like HEVC, representing an incremental improvement.
The paper tackles video compression artifacts by designing B-DRRN, a neural network that leverages block information to enhance compressed frame quality, achieving a 6.16% BD-rate reduction compared to the HEVC standard.
Although the video compression ratio nowadays becomes higher, the video coders such as H.264/AVC, H.265/HEVC, H.266/VVC always suffer from the video artifacts. In this paper, we design a neural network to enhance the quality of the compressed frame by leveraging the block information, called B-DRRN (Deep Recursive Residual Network with Block information). Firstly, an extra network branch is designed for leveraging the block information of the coding unit (CU). Moreover, to avoid a great increase in the network size, Recursive Residual structure and sharing weight techniques are applied. We also conduct a new large-scale dataset with 209,152 training samples. Experimental results show that the proposed B-DRRN can reduce 6.16% BD-rate compared to the HEVC standard. After efficiently adding an extra network branch, this work can improve the performance of the main network without increasing any memory for storing.