Metraipolis › archive › dc_6dbe5f45f5bb
VoRTeC: Taming Foundation Flow for One-step Real time Video Compression — arXiv:2609.02291
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02291
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T03:37:42.165Z
- SHA-256 of the archived text
65d527c5812f3b6056af5e9284839ca9eb4de72a2e76dccfd348147918b225a8- Stable URL of this page
https://metraipolis.com/documento/dc_6dbe5f45f5bb
How to cite
VoRTeC: Taming Foundation Flow for One-step Real time Video Compression — arXiv:2609.02291 — arXiv (en), https://arxiv.org/abs/2609.02291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6dbe5f45f5bb (Metraipolis archive dc_6dbe5f45f5bb, sha256 65d527c5812f3b6056af5e9284839ca9eb4de72a2e76dccfd348147918b225a8)
BibTeX
@misc{dc6dbe5f45f5bb,
title = {VoRTeC: Taming Foundation Flow for One-step Real time Video Compression — arXiv:2609.02291},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02291},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6dbe5f45f5bb; sha256 65d527c5812f3b6056af5e9284839ca9eb4de72a2e76dccfd348147918b225a8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Ultra-low bitrate video compression still faces critical challenges: traditional neural video compression inevitably introduces blurring artifacts, while diffusion-based generative video compression suffers from excessive decoding latency and poor temporal consistency. To address these issues, we propose $\mathtt{VoRTeC}$, a Video Compression framework built upon a foundational flow model (Wan2.1). By compactly encoding latent video representations, predicting the positions of compressed representations along flow trajectories, and integrating multi-scale priors, $\mathtt{VoRTeC}$ enables the compressor to harness generative video flow priors effectively. Without accessing the parameters or gradients of flow matching networks, our framework achieves one-step decoding and reconstructions with high perceptual fidelity. Meanwhile, we maintain consistency across frame groups via tail-frame reuse and prior caching. Extensive experiments demonstrate that our method reduces bit consumption by 58\% compared to prior diffusion-based approaches, with decoding speed boosted by 3 to 197 times: $\mathtt{VoRTeC}$ achieves a decoding speed of 13 FPS at 720p and 32 FPS at 480p.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.02291 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:13:12.530Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).