Related papers: Robust Super-Resolution GAN, with Manifold-based a…

Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high-dimensional, correlated data. While existing methods capture either aleatoric or epistemic…

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…

We combine generative adversarial network (GAN) with light microscopy to achieve deep learning super-resolution under a large field of view (FOV). By appropriately adopting prior microscopy data in an adversarial training, the neural…

Learning-based single image super-resolution (SISR) methods are continuously showing superior effectiveness and efficiency over traditional model-based methods, largely due to the end-to-end training. However, different from model-based…

In recent years, there have been several advancements in the task of image super-resolution using the state of the art Deep Learning-based architectures. Many super-resolution-based techniques previously published, require high-end and…

Super-Resolution (SR) is the problem that consists in reconstructing images that have been degraded by a zoom-out operator. This is an ill-posed problem that does not have a unique solution, and numerical approaches rely on a prior on…

Performing super-resolution of a depth image using the guidance from an RGB image is a problem that concerns several fields, such as robotics, medical imaging, and remote sensing. While deep learning methods have achieved good results in…

The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution. The loss function should encourage natural and perceptually pleasing results. A…

Real low-resolution (LR) face images contain degradations which are too varied and complex to be captured by known downsampling kernels and signal-independent noises. So, in order to successfully super-resolve real faces, a method needs to…

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual…

We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classification problems. Our method treats all training features…

Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. This task is known to be extremely difficult since it is an ill-posed problem. Recently, Convolutional…

This paper newly introduces multi-modality loss function for GAN-based super-resolution that can maintain image structure and intensity on unpaired training dataset of clinical CT and micro CT volumes. Precise non-invasive diagnosis of lung…

The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks. However, the quality of the automatically generated…

Despite that the performance of image-to-image translation has been significantly improved by recent progress in generative models, current methods still suffer from severe degradation in training stability and sample quality when applied…

Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural…

In the field of medical image analysis, there is a substantial need for high-resolution (HR) images to improve diagnostic accuracy. However, it is a challenging task to obtain HR medical images, as it requires advanced instruments and…

Although remarkable progress has been made on single image super-resolution due to the revival of deep convolutional neural networks, deep learning methods are confronted with the challenges of computation and memory consumption in…

State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution. However, when models are tested on corrupted images (e.g. due to scale changes,…

The perceptual loss has been widely used as an effective loss term in image synthesis tasks including image super-resolution, and style transfer. It was believed that the success lies in the high-level perceptual feature representations…