Research map / Video / Video generation
REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation
Haotian Wang, Yuzhe Weng, Jun Du, Haoran Xu, Xiaoyan Wu, Shan He, Bing Yin, Cong Liu, Qingfeng Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ID-Sink to the context cache (ablation) | REST ID-Context Cache · HDTF | FID: 19.362 -> 14.597 | Improved |
| add ID-Sink to the context cache (ablation) | REST ID-Context Cache · HDTF | FVD: 294.692 -> 219.870 | Improved |
| add ID-Sink to the context cache (ablation) | REST ID-Context Cache · HDTF | Sync-C: 8.345 -> 8.335 | No clear effect |
| add Context-Cache to ID-Sink (ablation) | REST ID-Context Cache · HDTF | Sync-C: 6.909 -> 8.335 | Improved |
| add Context-Cache to ID-Sink (ablation) | REST ID-Context Cache · HDTF | FID: 19.656 -> 14.597 | Improved |
| add Context-Cache to ID-Sink (ablation) | REST ID-Context Cache · HDTF | FVD: 271.508 -> 219.870 | Improved |
| add Smooth loss to ASD (ablation) | REST ASD · HDTF | FVD: 221.525 -> 219.870 | Improved |
| add Smooth loss to ASD (ablation) | REST ASD · HDTF | FID: 14.646 -> 14.597 | No clear effect |
| add Contrastive loss to ASD (ablation) | REST ASD · HDTF | FID: 15.278 -> 14.597 | Improved |
| add Contrastive loss to ASD (ablation) | REST ASD · HDTF | Sync-C: 8.190 -> 8.335 | Improved |
| add Contrastive loss to ASD (ablation) | REST ASD · HDTF | FVD: 219.881 -> 219.870 | No clear effect |
| add ASD distillation (ablation) | REST streaming student · HDTF | FID: 15.950 -> 14.597 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Sonic — Sonic: Shifting Focus to Global Audio Perception in Portrait Animation (CVPR 2025) · better on 5 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion (CVPR 2025 · similarity 0.87)
- Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion (NeurIPS 2026 · similarity 0.86)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.86)
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models (CVPR 2025 · similarity 0.86)
- MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation (AAAI 2025 · similarity 0.86)
- Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
