The Future of Video Compression—Moving Beyond Hybrid Codecs with Machine Learning

Metadata

Publisher: SMPTE
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE Motion Imaging Jour.
Volume: 133, No. 2, pp. 37–47
Abstract: The consumption of video content on the internet is increasing at a constant pace, along with an increase of video quality. As an answer to the ever-growing demand for high-quality video, compression technology improves steadily. About every decade, a new major video compression standard is issued, decreasing bitrate by a factor of two. Interestingly, the technology does not change radically between codecs generations. Instead, the same principles are re-used and pushed further. There have been several attempts to depart from this model, but none achieved to be competitive. Recently, the research community has started focusing on deep learning-based strategies, with speculation arising as to whether it could be a new contender to the classical approach. This paper analyzes the benefits and limitations of deep learning-based video compression methods and investigates practical aspects such as rate control, delay, memory consumption, and power consumption. Overlapping patch-based end-to-end video compression strategy is proposed to overcome memory limitations.
Publication Date: 2024-04-01
DOI: 10.5594/JMI.2024/IPYX8877
ISSN: Print: 1545-0279 | Electronic: 2160-2492
Link: https://doi.org/10.5594/JMI.2024/IPYX8877
Author(s): Thomas Guionnet
Marwa Tarchouli
Thomas Burnichon
Mickael Raulet
Keyword(s): Video Compression, Video Codec, MPEG-2, H.264, AVC, HEVC, VVC, Artificial Intelligence
Copyright: © 2024 SMPTE

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2024-IPYX8877__2024-SMPTEMIJAPRIL2024_17-17.json

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Thomas Guionnet, Marwa Tarchouli, Thomas Burnichon, and Mickael Raulet; The Future of Video Compression—Moving Beyond Hybrid Codecs with Machine Learning, MIJ 2024, Volume 133, Number 2 (pp. 37 to 47); SMPTE, 2024. Available at https://doi.org/10.5594/JMI.2024/IPYX8877

Snippet:

Thomas Guionnet, Marwa Tarchouli, Thomas Burnichon, and Mickael Raulet; The Future of Video Compression—Moving Beyond Hybrid Codecs with Machine Learning, MIJ 2024, Volume 133, Number 2 (pp. 37 to 47); SMPTE, 2024. Available at https://doi.org/10.5594/JMI.2024/IPYX8877

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Thomas Guionnet, Marwa Tarchouli, Thomas Burnichon, and Mickael Raulet; <cite>The Future of Video Compression—Moving Beyond Hybrid Codecs with Machine Learning</cite>, MIJ 2024, Volume 133, Number 2 (pp. 37 to 47); SMPTE, 2024. Available at <a href="https://doi.org/10.5594/JMI.2024/IPYX8877" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2024/IPYX8877</a></span>

SMPTE's HTML Pub

Preview:

Thomas Guionnet, Marwa Tarchouli, Thomas Burnichon, and Mickael Raulet; The Future of Video Compression—Moving Beyond Hybrid Codecs with Machine Learning, MIJ 2024, Volume 133, Number 2 (pp. 37 to 47); SMPTE, 2024
doi: 10.5594/JMI.2024/IPYX8877
url: https://doi.org/10.5594/JMI.2024/IPYX8877

Snippet:

<li>
Thomas Guionnet, Marwa Tarchouli, Thomas Burnichon, and Mickael Raulet; <cite id="bib-10-5594-jmi-2024-ipyx8877__2024-smptemijapril2024_17-17">The Future of Video Compression—Moving Beyond Hybrid Codecs with Machine Learning</cite>, MIJ 2024, Volume 133, Number 2 (pp. 37 to 47); SMPTE, 2024
<span class="doi">10.5594/JMI.2024/IPYX8877</span>
</li>