A neural-network inpainting variant of BUQO that turns local artefact hypothesis testing into a primal-dual optimization problem for Fourier and Radon imaging operators.
Very deep convolutional networks for large-scale image recognition,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A bilinear CNN that fuses features from a distortion-type classifier and an image classifier achieves superior BIQA performance on both synthetic and authentic distortion databases.
citing papers explorer
-
A Plug-and-Play Method with Inpainting Network for Bayesian Uncertainty Quantification in Imaging
A neural-network inpainting variant of BUQO that turns local artefact hypothesis testing into a primal-dual optimization problem for Fourier and Radon imaging operators.
-
Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
A bilinear CNN that fuses features from a distortion-type classifier and an image classifier achieves superior BIQA performance on both synthetic and authentic distortion databases.