UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing.
Meng CaoHaozhi HuangHao WangXuan WangLi ShenSheng WangLinchao BaoZhifeng LiJiebo LuoPublished in: CoRR (2021)
Keyphrases
- video editing
- temporally consistent
- temporal consistency
- optical flow
- video data
- depth map
- video camera
- superpixels
- video segmentation
- key frames
- video database
- facial expressions
- motion parameters
- face recognition
- face images
- temporal constraints
- video retrieval
- video streams
- video coding
- multi view
- video sequences
- temporal information
- three dimensional
- multiscale
- dynamic scenes
- object segmentation
- image classification
- motion estimation
- high quality
- image sequences