B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction

TL;DR

This paper introduces B-DRRN, a neural network leveraging block information for video compression artifacts reduction, achieving improved quality with minimal increase in model size.

Contribution

The paper proposes a novel neural network architecture that incorporates block information and recursive residual structures to enhance compressed video quality efficiently.

Findings

Reduces BD-rate by 6.16% compared to HEVC.

Uses block information to improve artifact reduction.

Employs recursive residual and weight sharing to keep model size small.

Abstract

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.