Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network.
Wenzhe ShiJose CaballeroFerenc HuszárJohannes TotzAndrew P. AitkenRob BishopDaniel RueckertZehan WangPublished in: CoRR (2016)
Keyphrases
- single image
- super resolution
- video super resolution
- convolutional neural network
- multiple images
- shape recovery
- d scene
- image pairs
- low resolution
- shape from shading
- high resolution
- face detection
- light source
- motion compensation
- neural network
- multi frame
- low resolution images
- high quality
- super resolved
- intrinsic images
- image sequences
- image processing
- motion estimation
- pixel level
- pairwise