Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling-Reference-Cited by-同舟云学术

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

Published:2024-07-13 Issue: Volume:21 Page:1-11
ISSN:
Container-title:Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24
language:
Short-container-title:

Author:

Shi Xiaoyu¹^ORCID,Huang Zhaoyang¹^ORCID,Wang Fu-Yun¹^ORCID,Bian Weikang¹^ORCID,Li Dasong¹^ORCID,Zhang Yi²^ORCID,Zhang Manyuan¹^ORCID,Cheung Ka Chun³^ORCID,See Simon³^ORCID,Qin Hongwei²^ORCID,Dai Jifeng⁴^ORCID,Li Hongsheng¹^ORCID

Affiliation:

1. The Chinese University of Hong Kong, Hong Kong

2. SenseTime, Hong Kong

3. NVIDIA, Hong Kong

4. Tsinghua University, China, China

Publisher

ACM

Reference82 articles.

1. Jianhong Bai, Tianyu He, Yuchi Wang, Junliang Guo, Haoji Hu, Zuozhu Liu, and Jiang Bian. 2024. UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing. arXiv preprint arXiv:2402.13185 (2024).

2. Max Bain, Arsha Nagrani, Gül Varol, and Andrew Zisserman. 2021. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In IEEE International Conference on Computer Vision.

3. Michael J Black and Padmanabhan Anandan. 1993. A framework for the robust estimation of optical flow. In 1993 (4th) International Conference on Computer Vision. IEEE, 231–236.

4. Andreas Blattmann, Tim Dockhorn, Sumith Kulal, Daniel Mendelevitch, Maciej Kilian, Dominik Lorenz, Yam Levi, Zion English, Vikram Voleti, Adam Letts, 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023).

5. Understanding Object Dynamics for Interactive Image-to-Video Synthesis