Communication Dans Un Congrès Année : 2024

Res-NeRV: Residual Blocks For A Practical Implicit Neural Video Decoder

Résumé

This paper proposes the integration of residual blocks into neural representation for videos (NeRV)-based architectures with the aim of enhancing the reconstruction of detailed patterns and high-level features. Additionally, a coding pipeline is introduced, placing the implicit neural decoder in a real-life video streaming framework. Indeed, DeepCABAC is employed for model compression, applying a quantization scheme followed by the context-adaptive binary arithmetic coding (CABAC) entropy coding algorithm, ultimately leading to bitstream generation. Our method outperforms NeRV, as well as x264 and x265, achieving BD-rate gains against NeRV: −12.06% using PSNR and −14.25% using MS-SSIM. Furthermore, it exhibits superior subjective quality compared to NeRV, attributed to enhanced high-level feature reconstruction. This observed behavior encourages the application of our method to other NeRV-based models, such as E-NeRV.

Fichier non déposé

Dates et versions

hal-04766987 , version 1 (05-11-2024)

Identifiants

Citer

Marwa Tarchouli, Thomas Guionnet, Marc Rivière, Wassim Hamidouche, Meriem Outtas, et al.. Res-NeRV: Residual Blocks For A Practical Implicit Neural Video Decoder. 2024 IEEE International Conference on Image Processing (ICIP), Oct 2024, Abu Dhabi, United Arab Emirates. pp.3751-3757, ⟨10.1109/icip51287.2024.10647402⟩. ⟨hal-04766987⟩
58 Consultations
0 Téléchargements

Altmetric

Partager

  • More