## ___***ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis***___

_**[Wangbo Yu*](https://scholar.google.com/citations?user=UOE8-qsAAAAJ&hl=zh-CN), [Jinbo Xing*](https://menghanxia.github.io), [Li Yuan*](), [Wenbo Hu†](https://wbhu.github.io/), [Xiaoyu Li](https://xiaoyu258.github.io/), [Zhipeng Huang](),
[Xiangjun Gao](https://scholar.google.com/citations?user=qgdesEcAAAAJ&hl=en/), [Tien-Tsin Wong](https://www.cse.cuhk.edu.hk/~ttwong/myself.html), [Ying Shan](https://scholar.google.com/citations?hl=en&user=4oXBp9UAAAAJ&view_op=list_works&sortby=pubdate), [Yonghong Tian†]()**_
## ๐ Introduction
ViewCrafter can generate high-fidelity novel views from