Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models.
Hyeonho JeongJong Chul YePublished in: CoRR (2023)
Keyphrases
- video editing
- input image
- image data
- multiscale
- video segmentation
- video data
- image classification
- diffusion models
- image analysis
- video database
- image retrieval
- segmentation method
- visual data
- video camera
- segmentation algorithm
- image features
- edge detection
- image segmentation
- multimedia
- image representation
- information retrieval
- keywords
- low level
- spatial information
- key frames
- object recognition
- video analysis