Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
StreamingEffect: Real-Time Human-Centric Video Effect Generation
Yiren Song, Cheng Liu, Yuxin Jiang +1
Streaming video effect generation is highly desirable for live human-centric applications such as e-commerce streaming, entertainment, and vlogging, yet remains difficult due to th…
cs.CV2026
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang +4
Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling step…