Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior.
Magauiya ZhussipShakarim SoltanayevSe Young ChunPublished in: CVPR (2019)
Keyphrases
- deep learning
- ground truth
- image prior
- test images
- image features
- input image
- blind deconvolution
- image data
- image restoration
- multiscale
- image representation
- colour images
- image content
- prior model
- single image
- edge preserving
- image segmentation
- image regions
- segmentation method
- image classification
- spatial information
- image denoising
- edge detection
- markov random field
- reconstructed image
- object detectors
- map estimation
- segmentation algorithm
- high resolution
- unsupervised learning