Towards zero-latency video transmission through frame extrapolation

Vijayaratnam, Melan; Cagnazzo, Marco; Valenzise, Giuseppe; Trioux, Anthony; Kieffer, Michel

Type de document :

Communication dans un congrès avec actes

DOI :

10.1109/icip46576.2022.9897958

Titre :

Towards zero-latency video transmission through frame extrapolation

Auteur(s) :

Vijayaratnam, Melan [Auteur]
Laboratoire Traitement et Communication de l'Information [LTCI]
Cagnazzo, Marco [Auteur]
Laboratoire Traitement et Communication de l'Information [LTCI]
Valenzise, Giuseppe [Auteur]
Laboratoire des signaux et systèmes [L2S]
Trioux, Anthony [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Kieffer, Michel [Auteur]
Laboratoire des signaux et systèmes [L2S]

Titre de la manifestation scientifique :

29th IEEE International Conference on Image Processing, ICIP 2022

Ville :

Bordeaux

Pays :

France

Date de début de la manifestation scientifique :

2022-10-16

Mot(s)-clé(s) en anglais :

Extrapolation
low-latency video delivery
video deep learning

Discipline(s) HAL :

Informatique [cs]
Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

In the past few years, several efforts have been devoted to reduce individual sources of latency in video delivery, including acquisition, coding and network transmission. The goal is to improve the quality of experience ...
Lire la suite >In the past few years, several efforts have been devoted to reduce individual sources of latency in video delivery, including acquisition, coding and network transmission. The goal is to improve the quality of experience in applications requiring real-time interaction. Nevertheless, these efforts are fundamentally constrained by technological and physical limits. In this paper, we investigate a radically different approach that can arbitrarily reduce the overall latency by means of video extrapolation. We propose two latency compensation schemes where video extrapolation is performed either at the encoder or at the decoder side. Since a loss of fidelity is the price to pay for compensating latency arbitrarily, we study the latency-fidelity compromise using three recent video prediction schemes. Our preliminary results show that by accepting a quality loss, we can compensate a typical latency of 100 ms with a loss of 8 dB in PSNR with the best extrapolator. This approach is promising but also suggests that further work should be done in video prediction to pursue zero-latency video transmission.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Vers un schéma de codage vidéo linéaire sans latence

Collections :