Search

Image Super-Resolution (ISR) is a technology that aims to increase image resolution while preserving as much content and detail as possible. In this study, we evaluate four different Deep Learning models (EDSR, LapSRN, ESPCN, and FSRCNN) to determine their effectiveness in increasing the resolution of lowresolution images. The study builds on previous research in the field as well as the results of the comparison between the different deep learning models. The problem statement for this study is: “Which of the four Deep Learning-based models, EDSR, LapSRN, ESPCN, and FSRCNN, generates an upscaled image with the best quality from a low-resolution image on a dataset of Abyssinian cats, with a factor of four, based on quantitative results?” The study utilizes a dataset consisting of pictures of Abyssinian cats to evaluate the performance and results of these different models. Based on the quantitative results obtained from RMSE, PSNR, and Structural Similarity (SSIM) measurements, our study concludes that EDSR is the most effective Deep Learning-based model., Bildsuperupplösning (ISR) är en teknik som syftar till att öka bildupplösningen samtidigt som så mycket innehåll och detaljer som möjligt bevaras. I denna studie utvärderar vi fyra olika Deep Learning modeller (EDSR, LapSRN, ESPCN och FSRCNN) för att bestämma deras effektivitet när det gäller att öka upplösningen på lågupplösta bilder. Studien bygger på tidigare forskning inom området samt resultatjämförelser mellan olika djupinlärningsmodeller. Problemet som studien tar upp är: “Vilken av de fyra Deep Learning-baserade modellerna, EDSR, LapSRN, ESPCN och FSRCNN generarar en uppskalad bild med bäst kvalité, från en lågupplöst bild på ett dataset med abessinierkatter, med skalningsfaktor fyra, baserat på kvantitativa resultat?” Studien använder en dataset av bilder på abyssinierkatter för att utvärdera prestandan och resultaten för dessa olika modeller. Baserat på de kvantitativa resultaten som erhölls från RMSE, PSNR och Structural Similarity (SSIM) mätningar, drar vår studie slutsatsen att EDSR är den mest effektiva djupinlärningsmodellen.

Image Super-Resolution (ISR) is a technology that aims to increase image resolution while preserving as much content and detail as possible. In this study, we evaluate four different Deep Learning models (EDSR, LapSRN, ESPCN, and FSRCNN) to determine their effectiveness in increasing the resolution of lowresolution images. The study builds on previous research in the field as well as the results of the comparison between the different deep learning models. The problem statement for this study is: “Which of the four Deep Learning-based models, EDSR, LapSRN, ESPCN, and FSRCNN, generates an upscaled image with the best quality from a low-resolution image on a dataset of Abyssinian cats, with a factor of four, based on quantitative results?” The study utilizes a dataset consisting of pictures of Abyssinian cats to evaluate the performance and results of these different models. Based on the quantitative results obtained from RMSE, PSNR, and Structural Similarity (SSIM) measurements, our study concludes that EDSR is the most effective Deep Learning-based model., Bildsuperupplösning (ISR) är en teknik som syftar till att öka bildupplösningen samtidigt som så mycket innehåll och detaljer som möjligt bevaras. I denna studie utvärderar vi fyra olika Deep Learning modeller (EDSR, LapSRN, ESPCN och FSRCNN) för att bestämma deras effektivitet när det gäller att öka upplösningen på lågupplösta bilder. Studien bygger på tidigare forskning inom området samt resultatjämförelser mellan olika djupinlärningsmodeller. Problemet som studien tar upp är: “Vilken av de fyra Deep Learning-baserade modellerna, EDSR, LapSRN, ESPCN och FSRCNN generarar en uppskalad bild med bäst kvalité, från en lågupplöst bild på ett dataset med abessinierkatter, med skalningsfaktor fyra, baserat på kvantitativa resultat?” Studien använder en dataset av bilder på abyssinierkatter för att utvärdera prestandan och resultaten för dessa olika modeller. Baserat på de kvantitativa resultaten som erhölls från RMSE, PSNR och Structural Similarity (SSIM) mätningar, drar vår studie slutsatsen att EDSR är den mest effektiva djupinlärningsmodellen.

Most existing approaches for single image super-resolution (SISR) resort to quality low-high resolution (LR-HR) pairs and available degradation kernels to train networks for a specific task in hand in a fully supervised manner. Labeled data used for training are, however, usually limited in terms of the quantity and the diversity degradation kernels. The learned SR networks with one degradation kernel (e.g., bicubic) do not generalize well and their performance sharply deteriorates on other kernels (e.g., blurred or noise). In this paper, we address the critical challenge for SISR: limited labeled LR images and degradation kernels. We propose a novel Semi-supervised Student-Teacher Super-Resolution approach called S2TSR that super-resolves both labelled and unlabeled LR images via adversarial learning. To better exploit the information from labeled LR images, we propose a student-teacher framework (S-T) via knowledge transfer from supervised learning (T) to unsupervised learning (S). Specifically, the S-T knowledge transfer is based on a shared SR network, partial weight sharing of dual discriminators, and a pair matching network which also plays as a ‘latent discriminator’. Lastly, to learn better features from the limited labeled LR images, we propose a new SR network via non-local and attention mechanisms. Experiments demonstrate that our approach substantially improves unsupervised methods and performs favorably over fully supervised methods. © 2021

Single image super resolution is the procedure of achieving a high resolution image from a low resolution image without any loss in the textural and structural information. First we apply the rational fractal interpolation model in the texture and non-texture region. Next, we develop an algorithm based on the proposed model. The scaling factor in the texture region is to be calculated. Even though our algorithm achieves a competitive performance with finer details, enhancing the sparsity will give a better result. Multispectral image denoising is attained using block diagonal representation. We generalize patch level representation via block diagonal matrix, investigate the proper choice of patch level transform and modifies through Single Value Decomposition(SVD). We demonstrate that a very competitive performance can be obtained through the combination of a proper global patch basis and local PCA.

Single image super resolution is the procedure of achieving a high resolution image from a low resolution image without any loss in the textural and structural information. First we apply the rational fractal interpolation model in the texture and non-texture region. Next, we develop an algorithm based on the proposed model. The scaling factor in the texture region is to be calculated. Even though our algorithm achieves a competitive performance with finer details, enhancing the sparsity will give a better result. Multispectral image denoising is attained using block diagonal representation. We generalize patch level representation via block diagonal matrix, investigate the proper choice of patch level transform and modifies through Single Value Decomposition(SVD). We demonstrate that a very competitive performance can be obtained through the combination of a proper global patch basis and local PCA.

Single image super resolution is the procedure of achieving a high resolution image from a low resolution image without any loss in the textural and structural information. First we apply the rational fractal interpolation model in the texture and non-texture region. Next, we develop an algorithm based on the proposed model. The scaling factor in the texture region is to be calculated. Even though our algorithm achieves a competitive performance with finer details, enhancing the sparsity will give a better result. Multispectral image denoising is attained using block diagonal representation. We generalize patch level representation via block diagonal matrix, investigate the proper choice of patch level transform and modifies through Single Value Decomposition(SVD). We demonstrate that a very competitive performance can be obtained through the combination of a proper global patch basis and local PCA.

Single image super resolution is the procedure of achieving a high resolution image from a low resolution image without any loss in the textural and structural information. First we apply the rational fractal interpolation model in the texture and non-texture region. Next, we develop an algorithm based on the proposed model. The scaling factor in the texture region is to be calculated. Even though our algorithm achieves a competitive performance with finer details, enhancing the sparsity will give a better result. Multispectral image denoising is attained using block diagonal representation. We generalize patch level representation via block diagonal matrix, investigate the proper choice of patch level transform and modifies through Single Value Decomposition(SVD). We demonstrate that a very competitive performance can be obtained through the combination of a proper global patch basis and local PCA.

This paper presents a spatial-varying minimum mean square error (MMSE)-based approach to construct super-resolution images from single source image of a lower resolution. The unique feature of this approach is that it works on a set of sub-images (also called multi-scale images) that are generated via decomposing the original source image. To do the decomposition, we design a number of low-pass filters with overlapped pass-bands so that sub-images are correlated with each other. Then, an MMSE-based estimation, involving all sub-images, is solved (after making use of the geometric-duality principle) to construct each missing pixel in the super-resolution image. Experimental results show that our new method offers a clearly-noticeable improvement over the existing MMSE-based methods (without decomposition). We believe that this is mainly attributing to the fact that both intra-scale and inter-scale correlations among the sub-images have been utilized in our approach. © 2012 IEEE.

This paper presents a spatial-varying minimum mean square error (MMSE)-based approach to construct super-resolution images from single source image of a lower resolution. The unique feature of this approach is that it works on a set of sub-images (also called multi-scale images) that are generated via decomposing the original source image. To do the decomposition, we design a number of low-pass filters with overlapped pass-bands so that sub-images are correlated with each other. Then, an MMSE-based estimation, involving all sub-images, is solved (after making use of the geometric-duality principle) to construct each missing pixel in the super-resolution image. Experimental results show that our new method offers a clearly-noticeable improvement over the existing MMSE-based methods (without decomposition). We believe that this is mainly attributing to the fact that both intra-scale and inter-scale correlations among the sub-images have been utilized in our approach. © 2012 IEEE.

The accurate registration of multiview images is of central importance in many advanced image processing applications. Image super-resolution, for example, is a typical application where the quality of the super-resolved image is degrading as registration errors increase. Popular registration methods are often based on features extracted from the acquired images. The accuracy of the registration is in this case directly related to the number of extracted features and to the precision at which the features are located: images are best registered when many features are found with a good precision. However, in low-resolution images, only a few features can be extracted and often with a poor precision. By taking a sampling perspective, we propose in this paper new methods for extracting features in low-resolution images in order to develop efficient registration techniques. We consider, in particular, the sampling theory of signals with finite rate of innovation and show that some features of interest for registration can be retrieved perfectly in this framework, thus allowing an exact registration. We also demonstrate through simulations that the sampling model which enables the use of finite rate of innovation principles is well suited for modeling the acquisition of images by a camera. Simulations of image registration and image super-resolution of artificially sampled images are first presented, analyzed and compared to traditional techniques. We finally present favorable experimental results of super-resolution of real images acquired by a digital camera available on the market.

Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing "the state-of-the-art" in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research.

Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing "the state-of-the-art" in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research.

Tato diplomová práce se zabývá zvyšováním rozlišení obrázků při zachování jejich dobré kvality. Jsou zde popsány současné metody řešení tohoto problému, dále jsou popsány principy fungování neuronových sítí se zaměřením na sítě konvoluční. Konečně je popsáno několik modelů konvoluční neuronové sítě pro zvýšení rozlišení obrazu na dvojnásobek, které byly natrénovány, otestovány a porovnány na nově vytvořené databázi fotografií lidí., This diploma thesis deals with image super-resolution with conservation of good quality. Firstly, there are described state of the art methods dealing with this problem, as well as principles of neural networks with focus on convolutional ones. Finally, there is described a few models of convolutional neural network for image super-resolution to double size, which have been trained, tested and compared on newly created database with pictures of people.

Tato práce se zabývá obarvováním šedotónového obrazu a zvětšováním rozlišení obrazu za pomoci neuronových sítí. Stručně vysvětluje principy neuronových sítí a shrnuje dosavadní přístupy v těchto oblastech. Dále pak popisuje návrh, implementaci a trénování různých architektur neuronových sítí. Nejlepší vytvořená architektura pro obarvování obrazu dokáže dobře obarvit především obrázky venkovních prostor. Architektura pro zvětšování rozlišení obrazu s reziduálními bloky, jež byla trénována s perceptuální chybovou funkcí, provádí dvojnásobné zvětšení rozlišení obrazu (celkem 4x více pixelů). Součástí této práce je také implementace webové aplikace, která využívá natrénované modely pro úpravu obrazu., This thesis deals with image colorization and image super-resolution using neural networks. It briefly explains neural networks principles and summarizes current approaches in this domain. It also describes the design, implementation and training of various neural network architectures. The best implemented architecture can colorize images, in particular, works well with outdoor areas. The architecture for image super-resolution with residual blocks that was trained with a perceptual loss function performs a double increase in image resolution (4x more pixels in total). Part of this thesis is also an implementation of a web application that uses trained models for image modification.

Tato práce se zabývá obarvováním šedotónového obrazu a zvětšováním rozlišení obrazu za pomoci neuronových sítí. Stručně vysvětluje principy neuronových sítí a shrnuje dosavadní přístupy v těchto oblastech. Dále pak popisuje návrh, implementaci a trénování různých architektur neuronových sítí. Nejlepší vytvořená architektura pro obarvování obrazu dokáže dobře obarvit především obrázky venkovních prostor. Architektura pro zvětšování rozlišení obrazu s reziduálními bloky, jež byla trénována s perceptuální chybovou funkcí, provádí dvojnásobné zvětšení rozlišení obrazu (celkem 4x více pixelů). Součástí této práce je také implementace webové aplikace, která využívá natrénované modely pro úpravu obrazu., This thesis deals with image colorization and image super-resolution using neural networks. It briefly explains neural networks principles and summarizes current approaches in this domain. It also describes the design, implementation and training of various neural network architectures. The best implemented architecture can colorize images, in particular, works well with outdoor areas. The architecture for image super-resolution with residual blocks that was trained with a perceptual loss function performs a double increase in image resolution (4x more pixels in total). Part of this thesis is also an implementation of a web application that uses trained models for image modification.

Tato diplomová práce se zabývá zvyšováním rozlišení obrázků při zachování jejich dobré kvality. Jsou zde popsány současné metody řešení tohoto problému, dále jsou popsány principy fungování neuronových sítí se zaměřením na sítě konvoluční. Konečně je popsáno několik modelů konvoluční neuronové sítě pro zvýšení rozlišení obrazu na dvojnásobek, které byly natrénovány, otestovány a porovnány na nově vytvořené databázi fotografií lidí., This diploma thesis deals with image super-resolution with conservation of good quality. Firstly, there are described state of the art methods dealing with this problem, as well as principles of neural networks with focus on convolutional ones. Finally, there is described a few models of convolutional neural network for image super-resolution to double size, which have been trained, tested and compared on newly created database with pictures of people.

Tato diplomová práce se zabývá zvyšováním rozlišení obrázků při zachování jejich dobré kvality. Jsou zde popsány současné metody řešení tohoto problému, dále jsou popsány principy fungování neuronových sítí se zaměřením na sítě konvoluční. Konečně je popsáno několik modelů konvoluční neuronové sítě pro zvýšení rozlišení obrazu na dvojnásobek, které byly natrénovány, otestovány a porovnány na nově vytvořené databázi fotografií lidí., This diploma thesis deals with image super-resolution with conservation of good quality. Firstly, there are described state of the art methods dealing with this problem, as well as principles of neural networks with focus on convolutional ones. Finally, there is described a few models of convolutional neural network for image super-resolution to double size, which have been trained, tested and compared on newly created database with pictures of people.

Tato práce se zabývá obarvováním šedotónového obrazu a zvětšováním rozlišení obrazu za pomoci neuronových sítí. Stručně vysvětluje principy neuronových sítí a shrnuje dosavadní přístupy v těchto oblastech. Dále pak popisuje návrh, implementaci a trénování různých architektur neuronových sítí. Nejlepší vytvořená architektura pro obarvování obrazu dokáže dobře obarvit především obrázky venkovních prostor. Architektura pro zvětšování rozlišení obrazu s reziduálními bloky, jež byla trénována s perceptuální chybovou funkcí, provádí dvojnásobné zvětšení rozlišení obrazu (celkem 4x více pixelů). Součástí této práce je také implementace webové aplikace, která využívá natrénované modely pro úpravu obrazu., This thesis deals with image colorization and image super-resolution using neural networks. It briefly explains neural networks principles and summarizes current approaches in this domain. It also describes the design, implementation and training of various neural network architectures. The best implemented architecture can colorize images, in particular, works well with outdoor areas. The architecture for image super-resolution with residual blocks that was trained with a perceptual loss function performs a double increase in image resolution (4x more pixels in total). Part of this thesis is also an implementation of a web application that uses trained models for image modification.