We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep ...

Remaining columns show the training images that produce feature vectors in the last hidden layer with the smallest Euclidean distance from the feature vector for the test image. We trained a large, ...

This paper proposes an end-to-end trained fully convolutional neural network model to process 3D image volumes. Unlike previous works that processed the input volumes slice-wise or patch-wise, the ...

Paper Summary: U-Net: Convolutional Networks for Biomedical Image Segmentation, MICCAI 2015 Olaf Ronneberger, Philipp Fischer, and Thomas Brox [DOI] In this paper, the authors proposed a fully ...

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep ...

The dataset consists of 500 natural images, ground-truth human annotations and benchmarking code. The data is explicitly separated into disjoint train, validation and test subsets. The dataset is an ...

We trained the network with 91-image dataset (without augmentation) and validated with Set5 dataset while training. At test time, to get the same result size for up-scaling factor 3. Also, we padded ...