Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image-Reference-Cited by-同舟云学术

Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image

Published:2023-10-26 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 31st ACM International Conference on Multimedia
language:
Short-container-title:

Author:

Shen Liao¹^ORCID,Li Xingyi¹^ORCID,Sun Huiqiang¹^ORCID,Peng Juewen¹^ORCID,Xian Ke²^ORCID,Cao Zhiguo¹^ORCID,Lin Guosheng³^ORCID

Affiliation:

1. Huazhong University of Science and Technology, Wuhan, China

2. Huazhong University of Science and Technology, Singapore, Singapore

3. Nanyang Technological University, Singapore, Singapore

Funder

The National Natural Science Foundation of China

Industry Collaboration Projects (IAF-ICP) Funding Initiative

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3581783.3612033

Reference40 articles.

1. Shengqu Cai , Eric Ryan Chan , Songyou Peng, Mohamad Shahbazi, Anton Obukhov, Luc Van Gool, and Gordon Wetzstein. 2022 . DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models . arXiv preprint arXiv:2211.12131 (2022). Shengqu Cai, Eric Ryan Chan, Songyou Peng, Mohamad Shahbazi, Anton Obukhov, Luc Van Gool, and Gordon Wetzstein. 2022. DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models. arXiv preprint arXiv:2211.12131 (2022).

2. Lucy Chai , Richard Tucker , Zhengqi Li , Phillip Isola , and Noah Snavely . 2023 . Persistent Nature: A Generative Model of Unbounded 3D Worlds. arXiv preprint arXiv:2303.13515 (2023). Lucy Chai, Richard Tucker, Zhengqi Li, Phillip Isola, and Noah Snavely. 2023. Persistent Nature: A Generative Model of Unbounded 3D Worlds. arXiv preprint arXiv:2303.13515 (2023).

3. Everybody Dance Now

4. Zhaoxi Chen , GuangcongWang, and Ziwei Liu . 2023 . Scenedreamer: Unbounded 3d scene generation from 2d image collections. arXiv preprint arXiv:2302.01330 (2023). Zhaoxi Chen, GuangcongWang, and Ziwei Liu. 2023. Scenedreamer: Unbounded 3d scene generation from 2d image collections. arXiv preprint arXiv:2302.01330 (2023).

5. Animating pictures with stochastic motion textures

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13

2. Procedurally generated AI compound media for expanding audial creations, broadening immersion and perception experience;International Journal of Electronics and Telecommunications;2024-06-25

3. State of the Art on Diffusion Models for Visual Computing;Computer Graphics Forum;2024-04-30