Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications

Networked video applications, e.g., video conferencing, often suffer from poor visual quality due to unexpected network fluctuation and limited bandwidth. In this paper, we have developed a Quality Enhancement Network (QENet) to reduce the video compression artifacts, leveraging the spatial and temp...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE International Conference on Image Processing (ICIP) pp. 934 - 938
Main Authors Lu, Ming, Cheng, Ming, Xu, Yiling, Pu, Shiliang, Shen, Qiu, Ma, Zhan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2019
Subjects
Cats
Convolutional codes
Gain
HEVC
multi-frame temporal priors
multi-scale spatial priors
Optical fiber networks
post-processing
Training
Video quality enhancement
Visualization
Xenon
Online AccessGet full text

Cover

More Information
Summary:Networked video applications, e.g., video conferencing, often suffer from poor visual quality due to unexpected network fluctuation and limited bandwidth. In this paper, we have developed a Quality Enhancement Network (QENet) to reduce the video compression artifacts, leveraging the spatial and temporal priors generated by respective multi-scale convolutions spatially and warped temporal predictions in a recurrent fashion temporally. We have integrated this QENet as a stand-alone post-processing subsystem to the High-Efficiency Video Coding (HEVC) compliant decoder. Experimental results show that our QENet demonstrates the state-of-the-art performance against default in-loop filters in HEVC and other deep learning based methods with noticeable objective gains in Peak Signal-to-Noise Ratio (PSNR) and subjective gains visually.
ISSN:2381-8549
DOI:10.1109/ICIP.2019.8803049