MLVC transmits entropy scale parameters via the hyperprior so that neural video decoding stays deterministic across different NPU vendors, achieving >70% BD-rate (MOS) gains over hardware HEVC in video-conferencing tests.
Generative latent video compression
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
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 reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.
ZeroGVC performs zero-shot generative video compression by guiding pretrained autoregressive diffusion priors with codebook noise vectors for P-frames after encoding the initial I-frame.
citing papers explorer
-
MLVC: Multi-platform Learned Video Codec for Real-World Deployment
MLVC transmits entropy scale parameters via the hyperprior so that neural video decoding stays deterministic across different NPU vendors, achieving >70% BD-rate (MOS) gains over hardware HEVC in video-conferencing tests.
-
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.
-
ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors
ZeroGVC performs zero-shot generative video compression by guiding pretrained autoregressive diffusion priors with codebook noise vectors for P-frames after encoding the initial I-frame.