arXiv 2609.116382026-09-11cs.CVcs.LG

Vidu S2：实时交互式、可编辑与空间视频生成

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Tsinghua University（清华大学）
Shengshu Technology（生数科技）

机构由 AI 辅助整理，请以论文原文为准。

Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang, Deyuan Liu, Jungang Li, Dechuang Chen, Ming Lin, Jingjiang Zhou, Haopeng Jin, Qi Jia, Xiaohang Wang, Yaole Wang, … 展开作者

Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang, Deyuan Liu, Jungang Li, Dechuang Chen, Ming Lin, Jingjiang Zhou, Haopeng Jin, Qi Jia, Xiaohang Wang, Yaole Wang, Zhanqiang Zhang, Ran Li, Zhengkun Huang, Shuyue Xiong, Yuji Wang, Zikun Dai, Hui He, Yang Luo, Mang Ning, Weiqi Feng, Chengyang Ye, Xinyue Lin, Min Zhao, Hongzhou Zhu, Hengkai Tan, Zeyuan Wang, Chendong Xiang, Kaiwen Zheng, Zhijie Deng, Fan Bao, Jianfei Chen, Jun Zhu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

中文总结 AI 辅助

Vidu S2包含实时交互数字角色模型与实时视频编辑模型，支持720p生成、动态参考和空间视频，性能优于所有基线。

中文摘要 AI 辅助

我们提出了Vidu S2，它包含Vidu S2-Avatar，一个实时交互的数字角色模型，以及Vidu S2-Editing，一个实时视频编辑模型。此外，我们探索了Vidu S2-Avatar和Vidu S2-Editing两者实时空间视频生成的可行性。与Vidu S1相比，Vidu S2-Avatar支持实时720p视频生成、支持可随时更新的动态参考生成，以及更强的指令遵循能力，例如跳舞。Vidu S2-Editing支持实时编辑视频流，包括风格渲染、服装替换、角色替换和背景替换。实验表明，Vidu S2在所有基线上表现更优。一个可玩的在线演示可在该https URL获取。

英文摘要

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation with dynamic references that can be updated at any moment, and stronger instruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, including style rendering, clothing replacement, character replacement, and background replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.