StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation.
Yupeng ZhouDaquan ZhouMing-Ming ChengJiashi FengQibin HouPublished in: CoRR (2024)
Keyphrases
- long range
- short range
- image data
- image representation
- image segmentation
- conditional random fields
- single image
- input image
- mrf models
- image retrieval
- segmentation algorithm
- segmentation method
- video data
- video sequences
- computer vision
- point trajectories
- long range interactions
- information retrieval
- figure ground
- pixel level
- video analysis
- energy function
- space time
- similarity measure