Spatial Rate Allocation for Learning-based Video Coding - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Spatial Rate Allocation for Learning-based Video Coding

Résumé

This paper presents a method that enables arbitrary end-to-end Learning-based image/video codecs to apply spatial rate allocation. At the frame-level, the forward pass of the underlying encoder network is followed by a latent refinement step, in which a customized loss function is minimized. This loss function takes as input an arbitrary pixel-wise map that defines the interest of each pixel and computes a weighted distortion with respect to the given interest map. Back-propagation of the customized loss function using the gradient descent gives a refined version of the frame latent in which the quality of regions of interest (ROI) is improved at the cost of quality of regions of disinterest. The proposed method is implemented on top of an existing end-to-end LVC, called AIVC 1 https://githuh.com/Orange-OpenSource/AIVC, using salience-based interest maps. Experiments show that the proposed method can effectively improve the quality of regions of interest frames. Notably, BD-BR performance using Weighted PSNR (WPSNR) shows an improvement of up to 21% by the proposed method.
Fichier principal
Vignette du fichier
Spatial Rate Allocation.pdf (669.64 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04382864 , version 1 (15-01-2024)

Identifiants

Citer

Mohsen Abdoli, Félix Henry, Gordon Clare, Abderrahmane Jarmouni, Kra-Tchimbie Koffi. Spatial Rate Allocation for Learning-based Video Coding. 2023 31st European Signal Processing Conference (EUSIPCO), Sep 2023, Helsinki, Finland. pp.580-584, ⟨10.23919/EUSIPCO58844.2023.10289782⟩. ⟨hal-04382864⟩
8 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More