LGVF: A Low-Bitrate Generative Video Compression Framework With Spatio-Temporal Diffusion Model
IEEE Signal Processing Letters · 2026 · 33 · 1280-1284
DOI: 10.1109/lsp.2026.3670748 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Mengmeng Zhang und 7 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Low-bitrate video compression remains a fundamental challenge in video coding. Recent advances in generative technologies show great potential for addressing this problem, yet existing generative models often suffer from uncontrollability caused by error accumulation and unpredictable semantic mutation. To tackle these issues, we propose a novel low-bitrate generative video compression framework based on a spatio-temporal diffusion model. A quality comparator is designed to select the optimal feature during generation, which effectively suppresses error accumulation. In addition, we design a Semantic Mutation Feature Extraction Network (SMFN) to accurately predict frame sequences, thereby effectively handling semantically mutated features. Extensive experiments demonstrate that our framework achieves superior performance on FVD and LPIPS metrics, significantly reducing bitrate while preserving both visual fidelity and semantic consistency.
Förderung
- Beijing Natural Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Zhang, M., Yu, Z., Lu, H., Li, Y., Cheng, R., Bai, H., Jing, H., & Liu, Z. (2026). LGVF: A Low-Bitrate Generative Video Compression Framework With Spatio-Temporal Diffusion Model. IEEE Signal Processing Letters, 33, 1280-1284. https://doi.org/10.1109/lsp.2026.3670748
Vancouver
Zhang M, Yu Z, Lu H, Li Y, Cheng R, Bai H, et al. LGVF: A Low-Bitrate Generative Video Compression Framework With Spatio-Temporal Diffusion Model. IEEE Signal Processing Letters. 2026;33:1280-1284. doi:10.1109/lsp.2026.3670748
BibTeX
@article{Zhang2026,
author = {Zhang, Mengmeng and Yu, Zihao and Lu, Hongyun and Li, Yuan and Cheng, Ran and Bai, Huihui and Jing, Hongyuan and Liu, Zhi},
title = {LGVF: A Low-Bitrate Generative Video Compression Framework With Spatio-Temporal Diffusion Model},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {1280--1284},
doi = {10.1109/lsp.2026.3670748}
}
EUVIMED