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
VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
Junlin Han, Filippos Kokkinos, Philip Torr
SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion
Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani
DreamMotion: Space-Time Self-Similarity Score Distillation for Zero-Shot Video Editing
Hyeonho Jeong, Jinho Chang, Geon Yeong Park, Jong Chul Ye
AICL: Action In-Context Learning for Video Diffusion Model
Jianzhi Liu, Junchen Zhu, Lianli Gao, Heng Tao Shen, Jingkuan Song