End-to-End Neural Video Compression: A Review

The pervasive presence of video content has spurred the development of advanced technologies to manage, process, and deliver high-quality content efficiently. Video compression is crucial in providing high-quality video services under limited network and storage capacities, traditionally achieved th...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiovana S. Gomes, Mateus Grellert, Fabio L. L. Ramos, Sergio Bampi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Circuits and Systems
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10962175/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849700488106213376
author Jiovana S. Gomes
Mateus Grellert
Fabio L. L. Ramos
Sergio Bampi
author_facet Jiovana S. Gomes
Mateus Grellert
Fabio L. L. Ramos
Sergio Bampi
author_sort Jiovana S. Gomes
collection DOAJ
description The pervasive presence of video content has spurred the development of advanced technologies to manage, process, and deliver high-quality content efficiently. Video compression is crucial in providing high-quality video services under limited network and storage capacities, traditionally achieved through hybrid codecs. However, as these frameworks reach a performance bottleneck with compression gains becoming harder to achieve with conventional methods, Deep Neural Networks (DNNs) offer a promising alternative. By leveraging DNNs’ nonlinear representation capacity, these networks can enhance compression efficiency and visual quality. Neural Video Coding (NVC) has recently received significant attention, with Neural Image Coding models surpassing traditional codecs in compression ratios. Therefore, this survey explores the state-of-the-art in NVC, examining recent works, frameworks, and the potential of this innovative approach to revolutionize video compression. We identify that NVC models have come a long way since the first proposals and currently are on par in compression efficiency with the latest hybrid codec, VVC. Still, many improvements are required to enable the practical usage of NVC, such as hardware-friendly development to enable faster inference and execution on mobile and energy-constrained devices.
format Article
id doaj-art-0a6d2a87f3424e63a49cab97eedc2c62
institution DOAJ
issn 2644-1225
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Circuits and Systems
spelling doaj-art-0a6d2a87f3424e63a49cab97eedc2c622025-08-20T03:18:15ZengIEEEIEEE Open Journal of Circuits and Systems2644-12252025-01-01612013410.1109/OJCAS.2025.355977410962175End-to-End Neural Video Compression: A ReviewJiovana S. Gomes0https://orcid.org/0000-0002-9910-7347Mateus Grellert1https://orcid.org/0000-0003-0600-7054Fabio L. L. Ramos2https://orcid.org/0000-0003-1107-8762Sergio Bampi3https://orcid.org/0000-0002-9018-6309Informatics Institute, Federal University of Rio Grande do Sul, Porto Alegre, BrazilInformatics Institute, Federal University of Rio Grande do Sul, Porto Alegre, BrazilComputer Engineering Course, Federal University of Pampa, Bagé, BrazilInformatics Institute, Federal University of Rio Grande do Sul, Porto Alegre, BrazilThe pervasive presence of video content has spurred the development of advanced technologies to manage, process, and deliver high-quality content efficiently. Video compression is crucial in providing high-quality video services under limited network and storage capacities, traditionally achieved through hybrid codecs. However, as these frameworks reach a performance bottleneck with compression gains becoming harder to achieve with conventional methods, Deep Neural Networks (DNNs) offer a promising alternative. By leveraging DNNs’ nonlinear representation capacity, these networks can enhance compression efficiency and visual quality. Neural Video Coding (NVC) has recently received significant attention, with Neural Image Coding models surpassing traditional codecs in compression ratios. Therefore, this survey explores the state-of-the-art in NVC, examining recent works, frameworks, and the potential of this innovative approach to revolutionize video compression. We identify that NVC models have come a long way since the first proposals and currently are on par in compression efficiency with the latest hybrid codec, VVC. Still, many improvements are required to enable the practical usage of NVC, such as hardware-friendly development to enable faster inference and execution on mobile and energy-constrained devices.https://ieeexplore.ieee.org/document/10962175/Video compressionlearned compressionautoencodertransformerneural networksneural video coding
spellingShingle Jiovana S. Gomes
Mateus Grellert
Fabio L. L. Ramos
Sergio Bampi
End-to-End Neural Video Compression: A Review
IEEE Open Journal of Circuits and Systems
Video compression
learned compression
autoencoder
transformer
neural networks
neural video coding
title End-to-End Neural Video Compression: A Review
title_full End-to-End Neural Video Compression: A Review
title_fullStr End-to-End Neural Video Compression: A Review
title_full_unstemmed End-to-End Neural Video Compression: A Review
title_short End-to-End Neural Video Compression: A Review
title_sort end to end neural video compression a review
topic Video compression
learned compression
autoencoder
transformer
neural networks
neural video coding
url https://ieeexplore.ieee.org/document/10962175/
work_keys_str_mv AT jiovanasgomes endtoendneuralvideocompressionareview
AT mateusgrellert endtoendneuralvideocompressionareview
AT fabiollramos endtoendneuralvideocompressionareview
AT sergiobampi endtoendneuralvideocompressionareview