An Efficient QP Variable Convolutional Neural Network Based In-loop Filter for Intra Coding

TL;DR

This paper introduces an efficient QP-aware convolutional neural network for in-loop filtering in VVC intra coding, improving compression efficiency with fewer parameters by capturing noise levels and emphasizing meaningful features.

Contribution

The paper proposes a novel QP attention module integrated into a controllable CNN architecture for intra coding, reducing model complexity while enhancing performance.

Findings

Achieves 4.03% BD-Rate savings on average for intra coding.

Outperforms QP-separate CNN models with fewer parameters.

Employs focal MSE loss to focus on challenging examples.

Abstract

In this paper, a novel QP variable convolutional neural network based in-loop filter is proposed for VVC intra coding. To avoid training and deploying multiple networks, we develop an efficient QP attention module (QPAM) which can capture compression noise levels for different QPs and emphasize meaningful features along channel dimension. Then we embed QPAM into the residual block, and based on it, we design a network architecture that is equipped with controllability for different QPs. To make the proposed model focus more on examples that have more compression artifacts or is hard to restore, a focal mean square error (MSE) loss function is employed to fine tune the network. Experimental results show that our approach achieves 4.03\% BD-Rate saving on average for all intra configuration, which is even better than QP-separate CNN models while having less model parameters.