We introduce unORANIC, an unsupervised approach that uses an adapted los...
Insufficient training data and severe class imbalance are often limiting...
Generative adversarial networks (GANs) and other adversarial methods are...
The most prominent problem associated with the deconvolution layer is th...
Significant advances have been made towards building accurate automatic
...
Convolutional neural networks have enabled accurate image super-resoluti...
In this note, we want to focus on aspects related to two questions most
...
Despite the breakthroughs in accuracy and speed of single image
super-re...
We propose a dual pathway, 11-layers deep, three-dimensional Convolution...