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

02/11/2022
by   Haoyue Tian, et al.
0

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 configuration.

READ FULL TEXT

page 2

page 4

research
12/05/2018

HEVC Inter Coding Using Deep Recurrent Neural Networks and Artificial Reference Pictures

The efficiency of motion compensated prediction in modern video codecs h...
research
08/17/2010

A symmetric motion picture of the twist-spun trefoil

With the aid of a computer, we provide a motion picture of the twist-spu...
research
11/05/2021

Versatile Learned Video Compression

Learned video compression methods have demonstrated great promise in cat...
research
02/21/2017

Projection based advanced motion model for cubic mapping for 360-degree video

This paper proposes a novel advanced motion model to handle the irregula...
research
03/08/2023

Scene Matters: Model-based Deep Video Compression

Video compression has always been a popular research area, where many tr...
research
07/28/2020

Efficient Adaptation of Neural Network Filter for Video Compression

We present an efficient finetuning methodology for neural-network filter...
research
06/19/2018

A Group Variational Transformation Neural Network for Fractional Interpolation of Video Coding

Motion compensation is an important technology in video coding to remove...

Please sign up or login with your details

Forgot password? Click here to reset