GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
This work proposes Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as the decoder, and the transmitted bitstream specifies its generation trajectory.
Ziyue Zeng, Xun Su, Hao-Yuan Liu et al.
· 3 citations
· ⚡1