Towards zero-latency video transmission through frame extrapolation

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

Document type :

Communication dans un congrès avec actes

DOI :

10.1109/icip46576.2022.9897958

Title :

Towards zero-latency video transmission through frame extrapolation

Author(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]

Conference title :

29th IEEE International Conference on Image Processing, ICIP 2022

City :

Bordeaux

Country :

France

Start date of the conference :

2022-10-16

English keyword(s) :

Extrapolation
low-latency video delivery
video deep learning

HAL domain(s) :

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

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Vers un schéma de codage vidéo linéaire sans latence

Collections :