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
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative 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.
MLVC achieves cross-platform robustness for neural video coding by sending scale parameters in the hyperprior, paired with gated memory, ReGLU activations, and perceptual training to reach over 70% BD-rate gains versus hardware HEVC while running at 100 FPS on Apple, Intel, and Qualcomm NPUs.
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.
-
MLVC: Multi-platform Learned Video Codec for Real-World Deployment
MLVC achieves cross-platform robustness for neural video coding by sending scale parameters in the hyperprior, paired with gated memory, ReGLU activations, and perceptual training to reach over 70% BD-rate gains versus hardware HEVC while running at 100 FPS on Apple, Intel, and Qualcomm NPUs.