Advanced Neural Network-Based Video Coding Technologies for Intra Prediction and In-Loop Filtering
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.07.2025 · 21 (7) · 1-23
DOI: 10.1145/3733108 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 18.07.2025. Verfasst von Yue Li und 11 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 46 Literaturangaben.
Abstract (Originalsprache)
The past decade has witnessed the huge success of deep learning in well-known artificial intelligence applications such as face recognition, autonomous driving, and large language model like ChatGPT. Recently, the application of deep learning has been extended to a much wider range, with Neural Network-Based Video Coding (NNVC) being one of them. NNVC can be performed at two different levels: embedding neural network-based (NN-based) coding tools into a classical video compression framework or building the entire compression framework upon neural networks. This article elaborates our studies in response to the recent exploration efforts in JVET (Joint Video Experts Team of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC29) in the name of NNVC, falling in the former category. Specifically, in this article, we propose two advanced NN-based video coding technologies, i.e., NN-based intra prediction and NN-based in-loop filtering, which have been investigated for several meeting cycles in JVET and then adopted into the reference software, i.e., NNVC. In addition, we further propose a Small Ad-hoc Deep-Learning Library (SADL), which provides integer-based inference capabilities for neural networks to ensure interoperability across different systems. SADL has been adopted as the inference platform of all neural networks in NNVC. Extensive experiments on top of the NNVC have been conducted to evaluate the effectiveness of the proposed techniques. Compared with VTM-11.0_nnvc, the proposed two NN-based coding tools jointly achieve {11.94%, 21.86%, 22.59%}, {9.18%, 19.76%, 20.92%}, and {10.63%, 21.56%, 23.02%} BD-rate reductions on average for {Y, Cb, Cr} under random-access, low-delay, and all-intra configurations, respectively.
Zitieren
APA
Li, Y., Li, J., Lin, C., Zhang, K., Zhang, L., Galpin, F., Dumas, T., Wang, H., Coban, M., Ström, J., Liu, D., & Andersson, K. (2025). Advanced Neural Network-Based Video Coding Technologies for Intra Prediction and In-Loop Filtering. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(7), 1-23. https://doi.org/10.1145/3733108
Vancouver
Li Y, Li J, Lin C, Zhang K, Zhang L, Galpin F, et al. Advanced Neural Network-Based Video Coding Technologies for Intra Prediction and In-Loop Filtering. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(7):1-23. doi:10.1145/3733108
BibTeX
@article{Li2025,
author = {Li, Yue and Li, Junru and Lin, Chaoyi and Zhang, Kai and Zhang, Li and Galpin, Franck and Dumas, Thierry and Wang, Hongtao and Coban, Muhammed and Ström, Jacob and Liu, Du and Andersson, Kenneth},
title = {Advanced Neural Network-Based Video Coding Technologies for Intra Prediction and In-Loop Filtering},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {7},
pages = {1--23},
doi = {10.1145/3733108}
}
EUVIMED