T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (12) · 10430-10438
DOI: 10.1609/aaai.v40i12.38014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhitao Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent advances in video generation techniques have given rise to an emerging paradigm of generative video coding for Ultra-Low Bitrate (ULB) scenarios by leveraging powerful generative priors. However, most existing methods are limited by domain specificity (e.g., facial or human videos) or excessive dependence on high-level text guidance, which tend to inadequately capture fine-grained motion details, leading to unrealistic or incoherent reconstructions. To address these challenges, we propose Trajectory-Guided Generative Video Coding (dubbed T-GVC), a novel framework that bridges low-level motion tracking with high-level semantic understanding. T-GVC features a semantic-aware sparse motion sampling pipeline that extracts pixel-wise motion as sparse trajectory points based on their semantic importance, significantly reducing the bitrate while preserving critical temporal semantic information. In addition, by integrating trajectory-aligned loss constraints into diffusion processes, we introduce a training-free guidance mechanism in latent space to ensure physically plausible motion patterns without sacrificing the inherent capabilities of generative models. Experimental results demonstrate that T-GVC outperforms both traditional and neural video codecs under ULB conditions. Furthermore, additional experiments confirm that our framework achieves more precise motion control than existing text-guided methods, paving the way for a novel direction of generative video coding guided by geometric motion modeling.
Zitieren
APA
Wang, Z., Man, H., Li, W., Wang, X., Fan, X., & Zhao, D. (2026). T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates. Proceedings of the AAAI Conference on Artificial Intelligence, 40(12), 10430-10438. https://doi.org/10.1609/aaai.v40i12.38014
Vancouver
Wang Z, Man H, Li W, Wang X, Fan X, Zhao D. T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(12):10430-10438. doi:10.1609/aaai.v40i12.38014
BibTeX
@article{Wang2026,
author = {Wang, Zhitao and Man, Hengyu and Li, Wenrui and Wang, Xingtao and Fan, Xiaopeng and Zhao, Debin},
title = {T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {12},
pages = {10430--10438},
doi = {10.1609/aaai.v40i12.38014}
}
EUVIMED