LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation.
Haoyu ZhengWenqiao ZhangYaoke WangHao ZhouJiang LiuJuncheng LiZheqi LvSiliang TangYueting ZhuangPublished in: CoRR (2024)
Keyphrases
- image content
- image data
- multiscale
- single image
- image representation
- image analysis
- image features
- image segmentation
- image classification
- image collections
- image pixels
- input image
- edge detection
- high resolution
- image retrieval
- web images
- pixel values
- control system
- keywords
- test images
- template matching
- scanned documents
- information retrieval
- text graphics
- region of interest
- image matching
- computer graphics
- feature points
- similarity measure