DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory.
Shengming YinChenfei WuJian LiangJie ShiHouqiang LiGong MingNan DuanPublished in: CoRR (2023)
Keyphrases
- fine grained
- coarse grained
- input image
- image segmentation
- access control
- image features
- image content
- image retrieval
- semantic labels
- tightly coupled
- image classification
- multimedia
- video content
- web images
- high resolution
- video sequences
- graph cuts
- video data
- image sequences
- information retrieval
- relational databases
- energy function
- database systems
- motion trajectories
- high level
- static images
- textual descriptions