GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS reduction over DCVC-RT.
Generative latent video compression,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A causal diffusion model reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.
citing papers explorer
-
GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS reduction over DCVC-RT.
-
A Causal Diffusion Model for Video Reconstruction from Ultra-Low-Bitrate Representations
A causal diffusion model reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.