TaoMate-FVSR: Audio-Guided Facial Video Restoration
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-03
Code: https://github.com/IceClear/St
Project page: https://taoliveaigc.github.io/TaoMate-FVSR
Terminology
Sources
- Wan: Open and Advanced Large-Scale Video Generative Models
- SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
- FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
- SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
- From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
- VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
- RGFVR: Reference-Guided Face Video Restoration with Flow Matching
- HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation Methods
- KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution
- Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
- Flow Matching for Generative Modeling
- TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis
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