Video ControlNet: Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models.
Ernie ChuShuo-Yen LinJun-Cheng ChenPublished in: CoRR (2023)
Keyphrases
- temporally consistent
- temporal consistency
- key frames
- video data
- image data
- video content
- video streams
- video sequences
- multiscale
- image features
- video frames
- single image
- input image
- three dimensional
- image segmentation
- image classification
- depth map
- optical flow
- superpixels
- feature points
- natural images
- segmentation method
- vector field
- high resolution
- test images
- image retrieval
- image sequences
- diffusion models