B-CANF: Adaptive B-Frame Coding With Conditional Augmented Normalizing Flows
IEEE Transactions on Circuits and Systems for Video Technology · 2024-04 · 34 (4) · 2908-2921
DOI: 10.1109/tcsvt.2023.3301016 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-04. Verfasst von Mu-Jung Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Science and Technology Council, Taiwan, MediaTek, and National Center for High-performance Computing.
Abstract (Originalsprache)
Over the past few years, learning-based video compression has become an active research area. However, most works focus on P-frame coding. Learned B-frame coding is under-explored and more challenging. This work introduces a novel B-frame coding framework, termed B-CANF, that exploits conditional augmented normalizing flows for B-frame coding. B-CANF additionally features two novel elements: frame-type adaptive coding and B*-frames. Our frame-type adaptive coding learns better bit allocation for hierarchical B-frame coding by dynamically adapting the feature distributions according to the B-frame type. Our B*-frames allow greater flexibility in specifying the group-of-pictures (GOP) structure by reusing the B-frame codec to mimic P-frame coding, without the need for an additional, separate P-frame codec. On commonly used datasets, B-CANF achieves the state-of-the-art compression performance as compared to the other learned B-frame codecs and shows comparable BD-rate results to HM-16.23 under the random access configuration in terms of PSNR. When evaluated on different GOP structures, our B*-frames achieve similar performance to the additional use of a separate P-frame codec.
Förderung
- National Science and Technology Council, Taiwan, MediaTek, and National Center for High-performance Computing
Zitieren
APA
Chen, M., Chen, Y., & Peng, W. (2024). B-CANF: Adaptive B-Frame Coding With Conditional Augmented Normalizing Flows. IEEE Transactions on Circuits and Systems for Video Technology, 34(4), 2908-2921. https://doi.org/10.1109/tcsvt.2023.3301016
Vancouver
Chen M, Chen Y, Peng W. B-CANF: Adaptive B-Frame Coding With Conditional Augmented Normalizing Flows. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(4):2908-2921. doi:10.1109/tcsvt.2023.3301016
BibTeX
@article{Chen2024,
author = {Chen, Mu-Jung and Chen, Yi-Hsin and Peng, Wen-Hsiao},
title = {B-CANF: Adaptive B-Frame Coding With Conditional Augmented Normalizing Flows},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {34},
number = {4},
pages = {2908--2921},
doi = {10.1109/tcsvt.2023.3301016}
}
EUVIMED