Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Network

05/10/2018
by   Xiaoyi He, et al.
0

In this paper, we propose a partition-masked Convolution Neural Network (CNN) to achieve compressed-video enhancement for the state-of-the-art coding standard, High Efficiency Video Coding (HECV). More precisely, our method utilizes the partition information produced by the encoder to guide the quality enhancement process. In contrast to existing CNN-based approaches, which only take the decoded frame as the input to the CNN, the proposed approach considers the coding unit (CU) size information and combines it with the distorted decoded frame such that the degradation introduced by HEVC is reduced more efficiently. Experimental results show that our approach leads to over 9.76 BD-rate saving on benchmark sequences, which achieves the state-of-the-art performance.

READ FULL TEXT

page 2

page 3

research
09/20/2017

Enhancing Quality for HEVC Compressed Videos

The latest High Efficiency Video Coding (HEVC) standard has been increas...
research
01/28/2019

Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure

In this paper, we propose a quality enhancement network for Versatile Vi...
research
02/22/2017

Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding

Inspired by the recent advances of image super-resolution using convolut...
research
08/09/2022

OL-DN: Online learning based dual-domain network for HEVC intra frame quality enhancement

Convolution neural network (CNN) based methods offer effective solutions...
research
09/23/2018

Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network

High efficiency video coding (HEVC) suffers high encoding computational ...
research
09/19/2017

Reducing Complexity of HEVC: A Deep Learning Approach

High Efficiency Video Coding (HEVC) significantly reduces bit-rates over...
research
02/28/2023

Valid Information Guidance Network for Compressed Video Quality Enhancement

In recent years deep learning methods have shown great superiority in co...

Please sign up or login with your details

Forgot password? Click here to reset