MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
2025-02-17
状态已发表
摘要In this paper, we present MVTokenFlow for high-quality 4D content creation from monocular videos. Recent advancements in generative models such as video diffusion models and multiview diffusion models enable us to create videos or 3D models. However, extending these generative models for dynamic 4D content creation is still a challenging task that requires the generated content to be consistent spatially and temporally. To address this challenge, MVTokenFlow utilizes the multiview diffusion model to generate multiview images on different timesteps, which attains spatial consistency across different viewpoints and allows us to reconstruct a reasonable coarse 4D field. Then, MVTokenFlow further regenerates all the multiview images using the rendered 2D flows as guidance. The 2D flows effectively associate pixels from different timesteps and improve the temporal consistency by reusing tokens in the regeneration process. Finally, the regenerated images are spatiotemporally consistent and utilized to refine the coarse 4D field to get a high-quality 4D field. Experiments demonstrate the effectiveness of our design and show significantly improved quality than baseline methods.
语种英语
DOIarXiv:2502.11697
相关网址查看原文
出处Arxiv
收录类别PPRN.PPRN
WOS记录号PPRN:121698959
WOS类目Computer Science, Software Engineering
资助项目National Natural Science Foundation of China[62206174]
文献类型预印本
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/514099
专题信息科学与技术学院_博士生
通讯作者Yang, Sibei
作者单位
1.ShanghaiTech Univ, Shanghai, Peoples R China
2.Hong Kong Univ Sci & Technol, Hong Kong, Peoples R China
3.Univ Hong Kong, Hong Kong, Peoples R China
推荐引用方式
GB/T 7714
Huang, Hanzhuo,Liu, Yuan,Zheng, Ge,et al. MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow. 2025.
条目包含的文件
条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Huang, Hanzhuo]的文章
[Liu, Yuan]的文章
[Zheng, Ge]的文章
百度学术
百度学术中相似的文章
[Huang, Hanzhuo]的文章
[Liu, Yuan]的文章
[Zheng, Ge]的文章
必应学术
必应学术中相似的文章
[Huang, Hanzhuo]的文章
[Liu, Yuan]的文章
[Zheng, Ge]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。