The technology, which has already been employed by several notable PC games over the last few years, uses machine learning to upscale rendered images in real-time. So rather than tasking the GPU with producing a native 4K image, the engine can render the game at a lower resolution and have DLSS make up the difference. In the case of DLSS, NVIDIA trained their neural network by taking low and high resolution images of the same game and having their in-house supercomputer analyze the differences. Combined with motion vector data, the neural network was tasked with not only filling in the necessary visual information to make the low resolution image better approximate the idealistic target, but predict what the next frame of animation might look like. In other words, if you have a computer powerful enough to run a game at 30 FPS in 1920 x 1080, the same computer could potentially reach 60 FPS if the game was rendered at 1280 x 720 and scaled up with DLSS.

Despite the rapid development of computational hardware, the treatment of large and high dimensional data sets is still a challenging problem. This paper provides a twofold contribution to the topic. First, we propose a Gaussian Mixture Model in conjunction with a reduction of the dimensionality of the data in each component of the model by principal component analysis, called PCA-GMM. To learn the (low dimensional) parameters of the mixture model we propose an EM algorithm whose M-step requires the solution of constrained optimization problems. Fortunately, these constrained problems do not depend on the usually large number of samples and can be solved efficiently by an (inertial) proximal alternating linearized minimization algorithm. Second, we apply our PCA-GMM for the superresolution of 2D and 3D material images based on the approach of Sandeep and Jacob. Numerical results confirm the moderate influence of the dimensionality reduction on the overall superresolution result.

AI tool turns low-pixel faces into realistic images A photo editing tool designed by a programming team at Duke University in Durham, North Carolina, raises prospects for sharper, cleaner images in digital presentations and also promises hours of fun for older-video game fans who can now generate crystal clear faces for low-pixel characters who populated early products. But the tool also unexpectedly brought to the surface concerns about bias in the use of datasets in massive machine learning projects. PULSE, Photo Upsampling via Latent Space Exploration, was created by Duke researchers to create more realistic images from low-pixel source data. In their research paper distributed earlier this year, the team explained how their approach differed from earlier efforts to generate lifelike images from 8-bit imagery. "Instead of starting with the low resolution image and slowly adding detail, PULSE traverses the high-resolution natural image manifold, searching for images that downscale to the original low resolution image," the report stated.

Researchers have figured out a way to transform a few dozen pixels into a high resolution image of a face using artificial intelligence. A team from Duke University in the US created an algorithm capable of "imagining" realistic-looking faces from blurry, unrecognisable pictures of people, with eight-times more effectiveness than previous methods. "Never have super-resolution images been created at this resolution before with this much detail," said Duke computer scientist Cynthia Rudin, who led the research. The images generated by the AI do not resemble real people, instead they are faces that look plausibly real. It therefore cannot be used to identify people from low resolution images captured by security cameras.

Optical Character Recognition and extraction is a key tool in the automatic evaluation of documents in a financial context. However, the image data provided to automated systems can have unreliable quality, and can be inherently low-resolution or downsampled and compressed by a transmitting program. In this paper, we illustrate the efficacy of a Gaussian Process upsampling model for the purposes of improving OCR and extraction through upsampling low resolution documents.

Super Resolution is the process of recovering a High Resolution (HR) image from a given Low Resolution (LR) image. An image may have a "lower resolution" due to a smaller spatial resolution (i.e. Clearly, on applying a degradation function, we obtain the LR image from the HR image. But, can we do the inverse? If we know the exact degradation function, by applying its inverse to the LR image, we can recover the HR image.

This article describes the techniques and training a deep learning model for image improvement, image restoration, inpainting and super resolution. This utilises many techniques taught in the Fastai course and makes use of the Fastai software library. This method of training a model is based upon methods and research by very talented AI researchers, I've credited them where I have been able to in the information and techniques. As far as I'm aware some of the techniques I've applied with the training data are unique at this point with these learning methods (as of February 2019) and only a handful of researchers are using all these techniques together, who will mostly are likely to be Fastai researchers/students. Super resolution is the process of upscaling and or improving the details within an image. Often a low resolution image is taken as an input and the same image is upscaled to a higher resolution, which is the output.

The extraction of a single high-quality image from a set of lowresolution images is an important problem which arises in fields such as remote sensing, surveillance, medical imaging and the extraction of still images from video. Typical approaches are based on the use of cross-correlation to register the images followed by the inversion of the transformation from the unknown high resolution image to the observed low resolution images, using regularization to resolve the ill-posed nature of the inversion process. In this paper we develop a Bayesian treatment of the super-resolution problem in which the likelihood function for the image registration parameters is based on a marginalization over the unknown high-resolution image. This approach allows us to estimate the unknown point spread function, and is rendered tractable through the introduction of a Gaussian process prior over images. Results indicate a significant improvement over techniques based on MAP (maximum a-posteriori) point optimization of the high resolution image and associated registration parameters. 1 Introduction The task in super-resolution is to combine a set of low resolution images of the same scene in order to obtain a single image of higher resolution. Provided the individual low resolution images have sub-pixel displacements relative to each other, it is possible to extract high frequency details of the scene well beyond the Nyquist limit of the individual source images.

The problem of super-resolution involves generating feasible higher resolution images, which are pleasing to the eye and realistic, from a given low resolution image. This might be attempted by using simple filters for smoothing out the high resolution blocks or through applications where substantial prior information is used to imply the textures and shapes which will occur in the images. In this paper we describe an approach which lies between the two extremes. It is a generic unsupervised method which is usable in all domains, but goes beyond simple smoothing methods in what it achieves. We use a dynamic treelike architecture to model the high resolution data. Approximate conditioning on the low resolution image is achieved through a mean field approach.

The problem of super-resolution involves generating feasible higher resolution images, which are pleasing to the eye and realistic, from a given low resolution image. This might be attempted by using simple filters for smoothing out the high resolution blocks or through applications where substantial prior information is used to imply the textures and shapes which will occur in the images. In this paper we describe an approach which lies between the two extremes. It is a generic unsupervised method which is usable in all domains, but goes beyond simple smoothing methods in what it achieves. We use a dynamic treelike architecture to model the high resolution data. Approximate conditioning on the low resolution image is achieved through a mean field approach.