Video Diffusion Model
Video diffusion models generate videos by iteratively removing noise from random data, guided by text prompts or other conditioning information. Current research focuses on improving temporal consistency, enhancing video quality (especially at high resolutions), and developing efficient algorithms for long video generation and various control mechanisms (e.g., camera control, object manipulation). These advancements are significant for applications in film production, animation, and 3D modeling, offering powerful tools for creating realistic and controllable video content.
Papers
Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting
Inkyu Shin, Qihang Yu, Xiaohui Shen, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen
CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
Dejia Xu, Weili Nie, Chao Liu, Sifei Liu, Jan Kautz, Zhangyang Wang, Arash Vahdat
I4VGen: Image as Free Stepping Stone for Text-to-Video Generation
Xiefan Guo, Jinlin Liu, Miaomiao Cui, Liefeng Bo, Di Huang
UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation
Xiang Wang, Shiwei Zhang, Changxin Gao, Jiayu Wang, Xiaoqiang Zhou, Yingya Zhang, Luxin Yan, Nong Sang
ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation
Shaoshu Yang, Yong Zhang, Xiaodong Cun, Ying Shan, Ran He
SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model
Zhengang Li, Yan Kang, Yuchen Liu, Difan Liu, Tobias Hinz, Feng Liu, Yanzhi Wang
Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
Zeyi Sun, Tong Wu, Pan Zhang, Yuhang Zang, Xiaoyi Dong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
Jiaojiao Fan, Haotian Xue, Qinsheng Zhang, Yongxin Chen
Controllable Longer Image Animation with Diffusion Models
Qiang Wang, Minghua Liu, Junjun Hu, Fan Jiang, Mu Xu
Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models
Qian Wang, Abdelrahman Eldesokey, Mohit Mendiratta, Fangneng Zhan, Adam Kortylewski, Christian Theobalt, Peter Wonka