BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization.
Yixin YangZhongzheng PengXiaoyu DuZhulin TaoJinhui TangJinshan PanPublished in: CoRR (2022)
Keyphrases
- feature fusion
- image prior
- video sequences
- multiple features
- space time
- feature extraction
- video data
- gray scale
- image restoration
- semantic information
- edge preserving
- markov random field
- edge information
- video frames
- image denoising
- maximum a posteriori
- key frames
- color images
- image deblurring
- image analysis
- computer vision
- least squares
- high level
- image segmentation
- image processing