Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding
ACM Transactions on Multimedia Computing, Communications, and Applications · 28.02.2023 · 19 (1s) · 1-22
DOI: 10.1145/3528173 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 23.01.2023. Verfasst von Yuzhang Hu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Research achievement of Key Laboratory of Science, Techonology and Standard in Press Industry.
Abstract (Originalsprache)
Modern codecs remove temporal redundancy of a video via inter prediction, i.e., searching previously coded frames for similar blocks and storing motion vectors to save bit-rates. However, existing codecs adopt block-level motion estimation, where a block is regressed by reference blocks linearly and is doomed to fail to deal with non-linear motions. In this article, we generate virtual reference frames (VRFs) with previously reconstructed frames via deep networks to offer an additional candidate, which is not constrained to linear motion structure and further significantly improves coding efficiency. More specifically, we propose a novel deep Auto-Regressive Moving-Average (ARMA) model, Error-Corrected Auto-Regressive Network (ECAR-Net), equipped with the powers of the conventional statistic ARMA models and deep networks jointly for reference frame prediction. Similar to conventional ARMA models, the ECAR-Net consists of two stages: Auto-Regression (AR) stage and Error-Correction (EC) stage, where the first part predicts the signal at the current time-step based on previously reconstructed frames, while the second one compensates for the output of the AR stage to obtain finer details. Different from the statistic AR models only focusing on short-term temporal dependency, the AR model of our ECAR-Net is further injected with the long-term dynamics mechanism, where long temporal information is utilized to help predict motions more accurately. Furthermore, ECAR-Net works in a configuration-adaptive way, i.e., using different dynamics and error definitions for the Low Delay B and Random Access configurations, which helps improve the adaptivity and generality in diverse coding scenarios. With the well-designed network, our method surpasses HEVC on average 5.0% and 6.6% BD-rate saving for the luma component under the Low Delay B and Random Access configurations and also obtains on average 1.54% BD-rate saving over VVC. Furthermore, ECAR-Net works in a configuration-adaptive way, i.e., using different dynamics and error definitions for the Low Delay B and Random Access configurations, which helps improve the adaptivity and generality in diverse coding scenarios.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Research achievement of Key Laboratory of Science, Techonology and Standard in Press Industry
- State Key Laboratory of Media Convergence Production Technology and Systems
Zitieren
APA
Hu, Y., Yang, W., Liu, J., & Guo, Z. (2023). Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(1s), 1-22. https://doi.org/10.1145/3528173
Vancouver
Hu Y, Yang W, Liu J, Guo Z. Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(1s):1-22. doi:10.1145/3528173
BibTeX
@article{Hu2023,
author = {Hu, Yuzhang and Yang, Wenhan and Liu, Jiaying and Guo, Zongming},
title = {Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2023},
volume = {19},
number = {1s},
pages = {1--22},
doi = {10.1145/3528173}
}
EUVIMED