CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 视频内容安全
Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
Jiang, Yanqin1,2; Zhang, Li3; Gao, Jin1,2; Hu, Weiming1,2,6; Yao, Yao4,5
Conference NameThe Twelfth International Conference on Learning Representations
Conference DateMay 7th, 2024 to May 11th, 2024
Conference PlaceVienna Austria

In this paper, we present Consistent4D, a novel approach for generating 4D dynamic objects from uncalibrated monocular videos. Uniquely, we cast the 360-degree dynamic object reconstruction as a 4D generation problem, eliminating the need for tedious multi-view data collection and camera calibration. This is achieved by leveraging the object-level 3D-aware image diffusion model as the primary supervision signal for training dynamic Neural Radiance Fields (DyNeRF). Specifically, we propose a cascade DyNeRF to facilitate stable convergence and temporal continuity under the time-discrete supervision signal. To achieve spatial and temporal consistency of the 4D generation, an interpolation-driven consistency loss is further introduced, which aligns the rendered frames with the interpolated frames from a pre-trained video interpolation model. Extensive experiments show that the proposed Consistent4D significantly outperforms previous 4D reconstruction approaches as well as per-frame 3D generation approaches, opening up new possibilities for 4D dynamic object generation from a single-view uncalibrated video. Project page:

Indexed ByEI
Sub direction classification三维视觉
planning direction of the national heavy laboratory实体人工智能系统感认知
Paper associated data
Document Type会议论文
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.School of Data Science, Fudan University
4.State Key Laboratory for Novel Software Technology, Nanjing University
5.School of Intelligence Science and Technology, Nanjing University
6.School of Information Science and Technology, ShanghaiTech University
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Jiang, Yanqin,Zhang, Li,Gao, Jin,et al. Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video[C],2024.
Files in This Item: Download All
File Name/Size DocType Version Access License
k5vgjk-5094_consiste(3186KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jiang, Yanqin]'s Articles
[Zhang, Li]'s Articles
[Gao, Jin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiang, Yanqin]'s Articles
[Zhang, Li]'s Articles
[Gao, Jin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiang, Yanqin]'s Articles
[Zhang, Li]'s Articles
[Gao, Jin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: k5vgjk-5094_consistent4d_consistent_360_dy.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.