PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models.
Yiming ZhangZhening XingYanhong ZengYouqing FangKai ChenPublished in: CoRR (2023)
Keyphrases
- input image
- image data
- single image
- image features
- image segmentation
- multiscale
- image content
- image representation
- template matching
- image classification
- image analysis
- edge detection
- image retrieval
- similarity measure
- region of interest
- random fields
- bayesian framework
- image pixels
- keypoints
- image regions
- visual effects
- test images
- segmentation algorithm
- spatial information
- feature points
- probabilistic model
- low level
- image processing
- vector field
- segmentation method
- information retrieval
- information extraction
- image collections
- text information