Turns pretrained video diffusion models into high-efficiency codecs, achieving high-quality reconstruction at extremely low bitrates (below 0.002 bpp) without retraining.
March 30, 2026
Original Paper
Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow
arXiv · 2603.26571
The Takeaway
By utilizing the internal ODE/SDE paths of foundation models as the compression mechanism, it enables video transmission at bitrates significantly lower than traditional or current neural codecs.
From the abstract
Existing generative video compression methods use generative models only as post-hoc reconstruction modules atop conventional codecs. We propose \emph{Generative Video Codec} (GVC), a zero-shot framework that turns a pretrained video generative model into the codec itself: the transmitted bitstream directly specifies the generative decoding trajectory, with no retraining required. To enable this, we convert the deterministic rectified-flow ODE of modern video foundation models into an equivalent