Invertible Neural Network-Based Video Compression

Zahra Montajabi, Vahid Ghassab, Nizar Bouguila

2023

Abstract

Due to the recent advent of high-resolution mobile and camera devices, it is necessary to develop an optimal solution for saving the new video content instead of traditional compression methods. Recently, video compression received enormous attention among computer vision problems in media technologies. Using state-of-the-art video compression methods, videos can be transmitted in a better quality requiring less band-width and memory. The advent of neural network-based video compression methods remarkably promoted video coding performance. In this paper, an Invertible Neural Network (INN) is utilized to reduce the information loss problem. Unlike the classic auto-encoders which lose some information during encoding, INN can preserve more information and therefore, reconstruct videos with more clear details. Moreover, they don’t increase the complexity of the network compared to traditional auto-encoders. The proposed method is evaluated on a public dataset and the experimental results show that the proposed method outperforms existing standard video encoding schemes such as H.264 and H.265 in terms of peak signal-to-noise ratio (PSNR), video multimethod assessment fusion (VMAF), and structural similarity index measure (SSIM).

Paper Citation

in Harvard Style

Montajabi Z., Ghassab V. and Bouguila N. (2023). Invertible Neural Network-Based Video Compression. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 558-564. DOI: 10.5220/0011807600003411

in Bibtex Style

@conference{icpram23,
author={Zahra Montajabi and Vahid Ghassab and Nizar Bouguila},
title={Invertible Neural Network-Based Video Compression},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={558-564},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011807600003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Invertible Neural Network-Based Video Compression
SN - 978-989-758-626-2
AU - Montajabi Z.
AU - Ghassab V.
AU - Bouguila N.
PY - 2023
SP - 558
EP - 564
DO - 10.5220/0011807600003411