REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents
机构 * Institute of Trustworthy Embodied AI, Fudan University(可信具身人工智能研究院,复旦大学) ; Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心) ; Microsoft Research(微软研究院)
专题命中 动作与事件理解 :video generation(abstract);分类 cs.CV
Comments Accepted to ICCV2025. Code available at https://github.com/microsoft/Reducio-VAE