Decoupled Self-Forcing Distillation for Streaming Talking Head Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2608.05663v3 Announce Type: replace Abstract: Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual co...
The paper introduces Routed Forcing, a method that improves audio‑driven streaming avatar generation by selectively applying different distillation objectives to semantic regions and noise stages. It uses Data‑Forcing Distillation on person regions at high noise levels to restore motion diversity, while retaining Distribution Matching Distillation for mouth and background to keep lip sync and scene stability. Experiments show up to 45% better dynamics and 7–25% higher diversity compared to the previous Self Forcing approach.
Real-time long-form avatar audio--video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas.
arXiv:2610.10343v1 Announce Type: new Abstract: Deploying a joint audio-video diffusion transformer for real-time, interactive generation normally requires two essential modifications: block-autoregr...
arXiv:2610.35594v1 Announce Type: new Abstract: Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has...
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.