RIFT: Residual-Informed Flow Transfer for One-Step Generative Video Compression
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
- Imagen Video: High Definition Video Generation with Diffusion Models
- Video Diffusion Models
- VideoPoet: A Large Language Model for Zero-Shot Video Generation
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
- Free-GVC: Toward Retraining-Free Extreme Generative Video Compression with Temporal Coherence
- Latte: Latent Diffusion Transformer for Video Generation
- Generative Neural Video Compression via Video Diffusion Prior
- Temporal Context Mining for Learned Video Compression
- Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression
- Bi-Directional Deep Contextual Video Compression
- Make-A-Video: Text-to-Video Generation without Text-Video Data
- Phenaki: Variable Length Video Generation From Open Domain Textual Description
- Wan: Open and Advanced Large-Scale Video Generative Models
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
- Open-Sora: Democratizing Efficient Video Production for All
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs