Predictive Coding for Animation-Based Video Compression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Predictive Coding for Animation-Based Video Compression

Résumé

We address the problem of efficiently compressing video for conferencing-type applications. We build on recent approaches based on image animation, which can achieve good reconstruction quality at very low bitrate by representing face motions with a compact set of sparse keypoints. However, these methods encode video in a frame-by-frame fashion, i.e., each frame is reconstructed from a reference frame, which limits the reconstruction quality when the bandwidth is larger. Instead, we propose a predictive coding scheme which uses image animation as a predictor, and codes the residual with respect to the actual target frame. The residuals can be in turn coded in a predictive manner, thus removing efficiently temporal dependencies. Our experiments indicate a significant bitrate gain, in excess of 70% compared to the HEVC video standard and over 30% compared to VVC, on a dataset of talking-head videos. Our code is available at github.com/animation-based-codecs.
Fichier principal
Vignette du fichier
RDAC.pdf (1.67 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04243836 , version 1 (16-10-2023)

Identifiants

Citer

Goluck Konuko, Stéphane Lathuilière, Giuseppe Valenzise. Predictive Coding for Animation-Based Video Compression. International Conference on Image Processing (ICIP’2023), Oct 2023, Kuala Lumpur (Malaysia), Malaysia. ⟨10.1109/icip49359.2023.10222205⟩. ⟨hal-04243836⟩
47 Consultations
28 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More