M3-CVC compresses video at ultra-low bitrates by encoding keyframes as discrete latents plus text prompts, then regenerates clips with a video diffusion model, claiming large rate reductions over VVC.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
M3-CVC: Controllable Video Compression with Multimodal Generative Models
M3-CVC compresses video at ultra-low bitrates by encoding keyframes as discrete latents plus text prompts, then regenerates clips with a video diffusion model, claiming large rate reductions over VVC.