UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing.
Meng CaoHaozhi HuangHao WangXuan WangLi ShenSheng WangLinchao BaoZhifeng LiJiebo LuoPublished in: IEEE Trans. Image Process. (2021)
Keyphrases
- video editing
- temporally consistent
- temporal consistency
- optical flow
- depth map
- video data
- superpixels
- video camera
- video segmentation
- video database
- motion parameters
- facial expressions
- key frames
- video sequences
- face recognition
- video streams
- face images
- segmentation method
- multi view
- high quality
- image sequences
- object segmentation
- temporal constraints
- video coding
- dynamic scenes
- video clips
- d scene
- motion estimation
- image processing
- face detection
- input image
- feature space
- three dimensional