Skip to content
AITNT · AI创作资讯·· 27 days agoAI score60

CUHK MMLab and others propose DuoMatching to improve the image quality of few-step video generation

少步视频生成不再牺牲画质!双重分布匹配方案实现又快又好

AI briefing

A team from CUHK MMLab, ByteDance and HKUST proposed DuoMatching, which lets a video generator accept both joint-distribution supervision and frame-level marginal-distribution supervision, introducing image priors during training without adding inference computation. Under the per-frame 2-step setting, the VBench total score rose from 80.67 to 83.53, the overall preference rate against all four baselines exceeded 80%, and the dynamic degree changed slightly from 94.44 to 93.61. The paper is public on arXiv, and the code and model weights are released together.

Open original aitntnews.com