Super Resolution
# Create super-resolution object.
obj = cv2.dnn_superres.DnnSuperResImpl_create()
# Path to the model.
obj.readModel(modelPath)
# Specify the method (one of "fsrcnn", "espcn", "lapsrn", "edsr") and scale.
obj.setModel(method, scale)
# Perform Upsampling
obj.upsample(image)References
- Deep Learning for Image Super-resolution: A Survey
- FSRCNN (Accelerating the Super-Resolution Convolutional Neural Network) - released in ECCV 2016
- ESPCN (Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network) - released in CVPR 2016
- EDSR (Enhanced Deep Residual Networks for Single Image Super-Resolution) - released in CVPR 2017
- LAPSRN (Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks) - released in CVPR 2017
- FSRCNN
- ESPCN
- LapSRN
- EDSR
Super Resolution