# Generative Neural Video Compression via Video Diffusion Prior arXiv: https://arxiv.org/abs/2512.05016 ยท HTML: https://mlsanity.com/paper/2512.05016/ ## Key facts - Cited by 18 papers in the map (data through 14 Oct 2026). - Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models. - Builds on 14 of its 55 references that are in the map. - First posted on arXiv 4 Dec 2025. ## Placed in - Diffusion models / [Diffusion for compression and wireless](https://mlsanity.com/diffusion/diffusion-for-compression-and-wireless/) ## Builds on (most cited first, 14 of 14) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024) - [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022) - [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024) - [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020) - [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023) - [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025) - [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024) - [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022) - [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020) - [Text + Sketch: Image Compression at Ultra Low Rates](https://mlsanity.com/paper/2307.01944/) (2023) - [StableCodec: Taming One-Step Diffusion for Extreme Image Compression](https://mlsanity.com/paper/2506.21977/) (2025) - [Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse](https://mlsanity.com/paper/2501.13528/) (2025) - [Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion](https://mlsanity.com/paper/2505.08281/) (2025) ## Built on by (most cited first, 18 of 18) - [GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow](https://mlsanity.com/paper/2603.26571/) (2026) - [DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression](https://mlsanity.com/paper/2601.20564/) (2026) - [ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling](https://mlsanity.com/paper/2603.17546/) (2026) - [ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors](https://mlsanity.com/paper/2606.22371/) (2026) - [Recent Advances of End-to-End Video Coding Technologies for AVS Standard Development](https://mlsanity.com/paper/2602.00483/) (2026) - [Generative Video Compression with Adaptive Score Distillation](https://mlsanity.com/paper/2607.22772/) (2026) - [GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates](https://mlsanity.com/paper/2608.04891/) (2026) - [KD-NVC: A Search-and-Distill Framework to Accelerate Neural Video Coding](https://mlsanity.com/paper/2606.04595/) (2026) - [Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling](https://mlsanity.com/paper/2607.19437/) (2026) - [GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression](https://mlsanity.com/paper/2608.03517/) (2026) - [CodecArena: Codec Quality Assessment via Visual Reinforcement Learning](https://mlsanity.com/paper/2608.09139/) (2026) - [Generative Video Compression Based on Hierarchical Referencing](https://mlsanity.com/paper/2608.11618/) (2026) - [DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer](https://mlsanity.com/paper/2608.20515/) (2026) - [VoRTeC: Taming Foundation Flow for One-step Real time Video Compression](https://mlsanity.com/paper/2609.02291/) (2026) - [Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality](https://mlsanity.com/paper/2609.27493/) (2026) - [A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos](https://mlsanity.com/paper/2610.05779/) (2026) - [Unified Generative Video Compression with Autoregressive and Bidirectional Video Diffusion](https://mlsanity.com/paper/2610.13023/) (2026) - [H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression](https://mlsanity.com/paper/2610.18125/) (2026) ## Abstract (arXiv) We present GNVC-VD, the first DiT-based generative neural video compression framework built upon an advanced video generation foundation model, where spatio-temporal latent compression and sequence-level generative refinement are unified within a single codec. Existing perceptual codecs primarily rely on pre-trained image generative priors to restore high-frequency details, but their frame-wise nature lacks temporal modeling and inevitably leads to perceptual flickering. To address this, GNVC-VD introduces a unified flow-matching latent refinement module that leverages a video diffusion transformer to jointly enhance intra- and inter-frame latents through sequence-level denoising, ensuring consistent spatio-temporal details. Instead of denoising from pure Gaussian noise as in video generation, GNVC-VD initializes refinement from decoded spatio-temporal latents and learns a correction term that adapts the diffusion prior to compression-induced degradation. A conditioning adaptor further injects compression-aware cues into intermediate DiT layers, enabling effective artifact removal while maintaining temporal coherence under extreme bitrate constraints. Extensive experiments show that GNVC-VD surpasses both traditional and learned codecs in perceptual quality and significantly reduces the flickering artifacts that persist in prior generative approaches, even below 0.01 bpp, highlighting the promise of integrating video-native generative priors into neural codecs for next-generation perceptual video compression.