DMVC: Decomposed Motion Modeling for Learned Video Compression
IEEE Transactions on Circuits and Systems for Video Technology · 2023-07 · 33 (7) · 3502-3515
DOI: 10.1109/tcsvt.2022.3233221 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-07. Verfasst von Kai Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, High Performance Computing Platform of Peking University.
Abstract (Originalsprache)
Inter prediction is the critical component in hybrid coding framework to deal with the temporal redundancy. Most of the neural video coding methods typically follow the motion compensation based inter coding scheme, establishing motion vector (MV) as the central role. In this paper, we innovatively propose an efficient motion modeling approach by inherently decomposing it into two components, the intrinsic motion and the compensatory motion. The intrinsic motion originates from the implicit spatiotemporal context hidden in the historical sequence, which can be intuitively captured free of bits. On the top of it, the compensatory motion acts a role of structural refinement and texture enhancement as a form of side information. In particular, the inter prediction is performed in the feature space as a manner of progressive temporal transition, conditioned on the decomposed motion. By the motion decomposition paradigm, we innovatively answer the question of motion representation, compensation and coding in the learned video compression framework. With the temporal prediction, the remaining pixel residue is signaled to obtain the reconstruction. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art coding performance on par with other end-to-end coding methods, and outperforms versatile video coding (VVC) under low-delay P (LDP) configuration in terms of MS-SSIM metric.
Förderung
- National Natural Science Foundation of China
- High Performance Computing Platform of Peking University
Zitieren
APA
Lin, K., Jia, C., Zhang, X., Wang, S., Ma, S., & Gao, W. (2023). DMVC: Decomposed Motion Modeling for Learned Video Compression. IEEE Transactions on Circuits and Systems for Video Technology, 33(7), 3502-3515. https://doi.org/10.1109/tcsvt.2022.3233221
Vancouver
Lin K, Jia C, Zhang X, Wang S, Ma S, Gao W. DMVC: Decomposed Motion Modeling for Learned Video Compression. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(7):3502-3515. doi:10.1109/tcsvt.2022.3233221
BibTeX
@article{Lin2023,
author = {Lin, Kai and Jia, Chuanmin and Zhang, Xinfeng and Wang, Shanshe and Ma, Siwei and Gao, Wen},
title = {DMVC: Decomposed Motion Modeling for Learned Video Compression},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2023},
volume = {33},
number = {7},
pages = {3502--3515},
doi = {10.1109/tcsvt.2022.3233221}
}
EUVIMED