Dilated convolutional neural network-based deep reference picture generation for video compression

TL;DR

This paper introduces a dilated CNN-based deep reference picture generator that enhances video compression by creating more relevant reference frames, leading to significant bit savings in VVC.

Contribution

It presents a novel deep reference picture generator using dilated CNNs integrated into VVC to improve motion compensation and compression efficiency.

Findings

Achieves 9.7% average bit savings in VVC.

Demonstrates improved reference picture relevance.

Validates effectiveness through comprehensive experiments.

Abstract

Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable reference for motion compensation. In this paper, we propose a deep reference picture generator which can create a picture that is more relevant to the current encoding frame, thereby further reducing temporal redundancy and improving video compression efficiency. Inspired by the recent progress of Convolutional Neural Network(CNN), this paper proposes to use a dilated CNN to build the generator. Moreover, we insert the generated deep picture into Versatile Video Coding(VVC) as a reference picture and perform a comprehensive set of experiments to evaluate the effectiveness of our network on the latest VVC Test Model VTM. The experimental results demonstrate that our proposed method achieves on average 9.7% bit saving compared with VVC under low-delay P configuration.