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