Integrating motion estimation and convolutional neural network for video super-resolution.
Tsung-Hsin WeiJu-Chin ChenPublished in: iCAST (2017)
Keyphrases
- video super resolution
- motion compensation
- motion estimation
- convolutional neural network
- super resolution
- motion compensated
- motion vectors
- video coding
- face detection
- block matching
- motion field
- low resolution
- inter frame
- motion model
- neural network
- video sequences
- image sequences
- image reconstruction
- multi frame
- reference frame
- high resolution
- optical flow
- high quality
- computational complexity
- vector field
- face recognition
- space time
- detection method
- pairwise
- spatio temporal
- three dimensional
- computer vision