VoRTeC: Taming Foundation Flow for One-step Real time Video Compression

arXiv:2609.02291 · cs.CV, cs.AI · Submitted 2026-09-02 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-02

Updated: 2026-09-03

Code: https://github.com/microsoft/DCVChttps:

Project page: https://darc8-sun.github.io/VoRTec_compress

License: http://creativecommons.org/licenses/by/4.0/

The gist: Ultra-low bitrate video compression still faces critical challenges: traditional neural video compression inevitably introduces blurring artifacts, while diffusion-based generative video compression

Terminology

Abstract

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, 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, 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: achieves a decoding speed of 13 FPS at 720p and 32 FPS at 480p.

Sources

Related papers