Saved in:
Bibliographic Details
Main Authors: Ramsook, Darren, Kokaram, Anil
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.18021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929230355365888
author Ramsook, Darren
Kokaram, Anil
author_facet Ramsook, Darren
Kokaram, Anil
contents At practical streaming bitrates, traditional video compression pipelines frequently lead to visible artifacts that degrade perceptual quality. This submission couples the effectiveness of a neural post-processor with a different dynamic optimsation strategy for achieving an improved bitrate/quality compromise. The neural post-processor is refined via adversarial training and employs perceptual loss functions. By optimising the post-processor and encoder directly our method demonstrates significant improvement in video fidelity. The neural post-processor achieves substantial VMAF score increases of +6.72 and +1.81 at bitrates of 50 kb/s and 500 kb/s respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2401_18021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Neural Enhancement Post-Processor with a Dynamic AV1 Encoder Configuration Strategy for CLIC 2024
Ramsook, Darren
Kokaram, Anil
Image and Video Processing
At practical streaming bitrates, traditional video compression pipelines frequently lead to visible artifacts that degrade perceptual quality. This submission couples the effectiveness of a neural post-processor with a different dynamic optimsation strategy for achieving an improved bitrate/quality compromise. The neural post-processor is refined via adversarial training and employs perceptual loss functions. By optimising the post-processor and encoder directly our method demonstrates significant improvement in video fidelity. The neural post-processor achieves substantial VMAF score increases of +6.72 and +1.81 at bitrates of 50 kb/s and 500 kb/s respectively.
title A Neural Enhancement Post-Processor with a Dynamic AV1 Encoder Configuration Strategy for CLIC 2024
topic Image and Video Processing
url https://arxiv.org/abs/2401.18021