4 papers
Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory
Yanbo Ding, Zhizhi Guo, Quanyue Song +4
Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video gen…
OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars
Quanyue Song, Yishan He, Yanbo Ding +4
Recent advances in diffusion-based generative models have enabled real-time audio-driven avatar generation and unified audio-visual synthesis, providing a promising foundation for…
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
Quanyue Song, Yishan He, Yanfei Zhang +6
Recent diffusion-based models have enabled realistic audio-driven avatar generation in real-time streaming. However, existing approaches struggle to maintain visual temporal consis…
Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation
Shihao Cheng, Jiaxu Zhang, Quanyue Song +6
Motion, speech, and sound effects are fundamental elements of human-centric videos, yet their heterogeneous temporal characteristics make joint generation highly challenging. Exist…