Information Bottleneck Driven Deep Video Compression—IBOpenDVCW
Entropy · 30.09.2024 · 26 (10) · 836
DOI: 10.3390/e26100836 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 30.09.2024. Verfasst von Timor Leiderman und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Electrical Engineering, Holon Institute of Technology, 52 Golomb Str., P.O. Box 305, Holon 58102, Israel. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Video compression remains a challenging task despite significant advancements in end-to-end optimized deep networks for video coding. This study, inspired by information bottleneck (IB) theory, introduces a novel approach that combines IB theory with wavelet transform. We perform a comprehensive analysis of information and mutual information across various mother wavelets and decomposition levels. Additionally, we replace the conventional average pooling layers with a discrete wavelet transform creating more advanced pooling methods to investigate their effects on information and mutual information. Our results demonstrate that the proposed model and training technique outperform existing state-of-the-art video compression methods, delivering competitive rate-distortion performance compared to the AVC/H.264 and HEVC/H.265 codecs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Electrical Engineering, Holon Institute of Technology, 52 Golomb Str., P.O. Box 305, Holon 58102, Israel.
ORCID-Profile: Timor Leiderman
Zitieren
APA
Leiderman, T., & Ben Ezra, Y. (2024). Information Bottleneck Driven Deep Video Compression—IBOpenDVCW. Entropy, 26(10), 836. https://doi.org/10.3390/e26100836
Vancouver
Leiderman T, Ben Ezra Y. Information Bottleneck Driven Deep Video Compression—IBOpenDVCW. Entropy. 2024;26(10):836. doi:10.3390/e26100836
BibTeX
@article{Leiderman2024,
author = {Leiderman, Timor and Ben Ezra, Yosef},
title = {Information Bottleneck Driven Deep Video Compression—IBOpenDVCW},
journal = {Entropy},
year = {2024},
volume = {26},
number = {10},
pages = {836},
doi = {10.3390/e26100836}
}
EUVIMED