Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding.
Gyeongman KimHajin ShimHyunsu KimYunjey ChoiJunho KimEunho YangPublished in: CVPR (2023)
Keyphrases
- video editing
- video encoding
- temporally consistent
- low complexity
- temporal consistency
- video data
- video camera
- video database
- video segmentation
- optical flow
- motion estimation
- key frames
- depth map
- superpixels
- video coding
- video encoder
- denoising
- video clips
- multimedia
- video retrieval
- video frames
- high quality
- multi view
- d objects
- computational complexity
- three dimensional
- computer vision