Cartoon single-image super-resolution approach based on generative adversarial network

Single image super-resolution (SISR) is of great importance as a low-level computer vision task. The fast development of Generative Adversarial Network (GAN) based deep learning architectures realises an efficient and effective SISR to boost the spatial resolution of natural images captured by digital cameras. However, the SISR for medical images is still a very challenging problem. This is due to (1) compared to natural images, in general, medical images have lower signal to noise ratios, (2) GAN based models pre-trained on natural images may synthesise unrealistic patterns in medical images which could affect the clinical interpretation and diagnosis, and (3) the vanilla GAN architecture may suffer from unstable training and collapse mode that can also affect the SISR results. In this paper, we propose a novel lesion focused SR (LFSR) method, which incorporates GAN to achieve perceptually realistic SISR results for brain tumour MRI images. More importantly, we test and make comparison using recently developed GAN variations, e.g., Wasserstein GAN (WGAN) and WGAN with Gradient Penalty (WGAN-GP), and propose a novel multi-scale GAN (MS-GAN), to achieve a more stabilised and efficient training and improved perceptual quality of the super-resolved results. Based on both quantitative evaluations and our designed mean opinion score, the proposed LFSR coupled with MS-GAN has performed better in terms of both perceptual quality and efficiency.

Generative adversarial network (GAN) has been widely applied to produce super-resolution (SR) image with real perception and texture details. In most existing SR approaches, the training objective typically measures a pixel-wise average distance between the SR and high-resolution (HR) images. However, as the degradation function of different images from HR to low resolution (LR) is generally different, optimizing such metrics often leads to certain unpleasant artificial traces. Unlike the prevalent GAN inversion methods that require expensive image-specific optimization at runtime, we present an alternative formulation by directly leveraging latent representation produced by a pretrained AutoEncoder. We call this improved method reduce dimension super-resolved GAN (RD-SRGAN). RD-SRGAN first obtains the latent feature representation of LR image by a pretrained AutoEncoder as input to the generator network. This process not only reduces noise effects but also decreases the overall computational complexity. On the other hand, the residual between the ground truth and the produced images replaces the produced images as input to the discriminator network, and a 2D zero mean Gaussian noise with controllable low variance replaces the real images as another input to the discriminator network. By leveraging the feature representation and properties of the 2D zero mean Gaussian noise, we restrict the optimization space to produce an SR image. Therefore, the residual of the generated SR images tend to approximates to a Gaussian noise, which introduces useless deviation information as little as possible. Experimental results show that RD-SRGAN can benefit from these strategies and achieve improved fidelity and naturalness comparison to existing methods. Switching the pretrained AutoEncoder allows the method to deal with images from diverse categories, e.g., remote sensing satellite imaging, medical imaging, and astronomy.

Single Image Super-Resolution (SISR) stands at the forefront of image processing, offering a transformative solution to elevate low-resolution images to a higher fidelity.Leveraging deep neural networks, particularly Generative Adversarial Networks (GANs), this study aims to enrich the quality of images, especially in domains like medical imaging, public surveillance, and historical image restoration. Traditional methods often fail to preserve crucial details during up scaling, prompting the adoption of deep learning techniques which have demonstrated remarkable breakthroughs in accuracy and efficiency. By harnessing the adversarial training process inherent in GANs, we seek to propel the boundaries of image enhancement, striving to faithfully reconstruct high-resolution renditions while retaining essential nuances from their low-resolution counterparts. Through comprehensive performance evaluations utilizing publicly available datasets, we conduct rigorous quantitative and qualitative analyses to gauge the efficacy of various GAN architectures in SISR. This meticulous examination allows us to assess not only the fidelity of the reconstructed images but also the computational efficiency and scalability of each approach, essential considerations for real-world applications. However, alongside the promises of GAN-based SISR come inherent challenges that warrant attention. Issues such as training instability, mode collapse, and imageartifacts present hurdles that must be addressed to fully harness the potential of GANs in image enhancement.Additionally, the integration of domain-specific expertise, particularly in fields like medical imaging, can further enhance the utility and efficacy of GAN-based super-resolution techniques.In conclusion, while the journey towards achieving high-quality, high-resolution images may be fraught with challenges, the integration of GANs into SISR represents a significant leap forward, promising to revolutionize various industries and deepen our understanding of visual data.

Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires the patient to remain still for long periods of time, which causes patient discomfort and increases the probability of motion induced image artifacts. A possible solution is to acquire low resolution (LR) images and to process them with the Super Resolution Generative Adversarial Network (SRGAN) to create a super-resolved version. This work applies SRGAN to MR images of the prostate and performs three experiments. The first experiment explores improving the in-plane MR image resolution by factors of 4 and 8, and shows that, while the PSNR and SSIM (Structural SIMilarity) metrics are lower than the isotropic bicubic interpolation baseline, the SRGAN is able to create images that have high edge fidelity. The second experiment explores anisotropic super-resolution via synthetic images, in that the input images to the network are anisotropically downsampled versions of HR images. This experiment demonstrates the ability of the modified SRGAN to perform anisotropic super-resolution, with quantitative image metrics that are comparable to those of the anisotropic bicubic interpolation baseline. Finally, the third experiment applies a modified version of the SRGAN to super-resolve anisotropic images obtained from the through-plane slices of the volumetric MR data. The output super-resolved images contain a significant amount of high frequency information that make them visually close to their HR counterparts. Overall, the promising results from each experiment show that super-resolution for MR images is a successful technique and that producing isotropic MR image volumes from anisotropic slices is an achievable goal.

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing unsupervised real-world SISR methods adopt a two-stage training strategy by synthesizing realistic LR images from their HR counterparts first, then training the super-resolution (SR) models in a supervised manner. However, the training of image degradation and SR models in this strategy are separate, ignoring the inherent mutual dependency between downscaling and its inverse upscaling process. Additionally, the ill-posed nature of image degradation is not fully considered. In this paper, we propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly. The main idea of SDFlow is to decouple image content and degradation information in the latent space, where content information distribution of LR and HR images is matched in a common latent space. Degradation information of the LR images and the high-frequency information of the HR images are fitted to an easy-to-sample conditional distribution. Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.

To reduce external disturbances and achieve high vertical resolution, the scanning time for white-light interference microscopy is very short. Because capturing high-resolution (HR) images is time consuming, low-resolution (LR) images are acquired instead. However, HR images are more desirable because they contain more details. To ensure high vertical resolution and high image resolution, one feasible solution is to process the scanned LR images to HR images by single image super-resolution (SISR). In this paper, an interference image super-resolution (IISR) model based on a generative adversarial network (GAN) is proposed. The generator is based on the enhanced super-resolution generative adversarial network (ESRGAN) architecture. With the aim of acquiring more realistic images, the discriminator network is designed using a modified DenseNet architecture, in which the pooling layers are replaced with dilated convolutional layers. The perceptual loss is optimized, and the content loss is upgraded to a continuously differentiable piecewise function. Various microscopy images are tested, including images with and without interference fringes. The IISR model has been proven to restore LR images to HR images. The comparative experiments prove that the proposed model achieves better visual quality than other models, preserving more realistic details.

High resolution images obtained from single image super resolution often suffer from excessive smoothness which blurs edges and gives smooth areas an un-natural texture. This paper proposes a super resolution method that combines wavelet super resolution and an edge enhancing back-projection filter to produce a super resolution image with sharp edges and natural texture. The low resolution image is first up-sampled using the discrete wavelet transform. High frequency sub-bands are derived from DWT of a bicubic interpolated low resolution image. The up-sampled image is then subjected to iterative back projection using a back-projection filter based on the Laplacian of Gaussian. The proposed method is tested on RGB colour images. It is found to produce better results than bicubic interpolation and selected edge directed interpolation methods in terms of PSNR and SSIM. It is also found to approximate the edge sharpness of edge directed interpolation while giving a more natural texture in smooth areas. The proposed method also eliminates spurious colours that have been observed in most edge-directed methods.

Deep convolutional neural networks (CNNs), trained on corresponding pairs of high- and low-resolution images, achieve state-of-the-art performance in single-image super- resolution and surpass previous signal-processing based approaches. However, their performance is limited when applied to real photographs. The reason lies in their train- ing data: low-resolution (LR) images are obtained by bicu- bic interpolation of the corresponding high-resolution (HR) images. The applied convolution kernel significantly differs from real-world camera-blur. Consequently, while current CNNs well super-resolve bicubic-downsampled LR images, they often fail on camera-captured LR images. To improve generalization and robustness of deep super- resolution CNNs on real photographs, we present a ker- nel modeling super-resolution network (KMSR) that incor- porates blur-kernel modeling in the training. Our pro- posed KMSR consists of two stages: we first build a pool of realistic blur-kernels with a generative adversarial net- work (GAN) and then we train a super-resolution network with HR and corresponding LR images constructed with the generated kernels. Our extensive experimental vali- dations demonstrate the effectiveness of our single-image super-resolution approach on photographs with unknown blur-kernels.

Many deep learning (DL) frameworks have demonstrated state-of-the-art performance in the super-resolution (SR) task of magnetic resonance imaging, but most performances have been achieved with simulated low-resolution (LR) images rather than LR images from real acquisition. Due to the limited generalizability of the SR network, enhancement is not guaranteed for real LR images because of the unreality of the training LR images. In this study, we proposed a DL-based SR framework with an emphasis on data construction to achieve better performance on real LR MR images. The framework comprised two steps: (a) downsampling training using a generative adversarial network (GAN) to construct more realistic and perfectly matched LR/high-resolution (HR) pairs. The downsampling GAN input was real LR and HR images. The generator translated the HR images to LR images and the discriminator distinguished the patch-level difference between the synthetic and real LR images. (b) SR training was performed using an enhance4d deep super-resolution network (EDSR). In the controlled experiments, three EDSRs were trained using our proposed method, Gaussian blur, and k-space zero-filling. As for the data, liver MR images were obtained from 24 patients using breath-hold serial LR and HR scans (only HR images were used in the conventional methods). The k-space zero-filling group delivered almost zero enhancement on the real LR images and the Gaussian group produced a considerable number of artifacts. The proposed method exhibited significantly better resolution enhancement and fewer artifacts compared with the other two networks. Our method outperformed the Gaussian method by an improvement of 0.111 ± 0.016 in the structural similarity index and 2.76 ± 0.98 dB in the peak signal-to-noise ratio. The blind/reference-less image spatial quality evaluator metric of the conventional Gaussian method and proposed method were 46.6 ± 4.2 and 34.1 ± 2.4, respectively.

The deep learning models for the Single Image Super-Resolution (SISR) task have found success in recent years. However, one of the prime limitations of existing deep learning-based SISR approaches is that they need supervised training. Specifically, the Low-Resolution (LR) images are obtained through known degradation (for instance, bicubic downsampling) from the High-Resolution (HR) images to provide supervised data as an LR-HR pair. Such training results in a domain shift of learnt models when real-world data is provided with multiple degradation factors not present in the training set. To address this challenge, we propose an unsupervised approach for the SISR task using Generative Adversarial Network (GAN), which we refer to hereafter as DUS-GAN. The novel design of the proposed method accomplishes the SR task without degradation estimation of real-world LR data. In addition, a new human perception-based quality assessment loss, i.e., Mean Opinion Score (MOS), has also been introduced to boost the perceptual quality of SR results. The pertinence of the proposed method is validated with numerous experiments on different reference-based (i.e., NTIRE Real-world SR Challenge validation dataset) and no-reference based (i.e., NTIRE Real-world SR Challenge Track-1 and Track-2) testing datasets. The experimental analysis demonstrates committed improvement from the proposed method over the other state-of-the-art unsupervised SR approaches, both in terms of subjective and quantitative evaluations on different reference metrics (i.e., LPIPS, PI-RMSE graph) and no-reference quality measures such as NIQE, BRISQUE and PIQE. We also provide the implementation of the proposed approach (https://github.com/kalpeshjp89/DUSGAN) to support reproducible research.

Generating High-Resolution Climate Prediction through Generative Adversarial Network

Example learning-based image super-resolution (SR) is recognized as an effective way to produce a high-resolution (HR) image with the help of an external training set. The effectiveness of learning-based SR methods, however, depends highly upon the consistency between the supporting training set and low-resolution (LR) images to be handled. To reduce the adverse effect brought by incompatible high-frequency details in the training set, we propose a single image SR approach by learning multiscale self-similarities from an LR image itself. The proposed SR approach is based upon an observation that small patches in natural images tend to redundantly repeat themselves many times both within the same scale and across different scales. To synthesize the missing details, we establish the HR-LR patch pairs using the initial LR input and its down-sampled version to capture the similarities across different scales and utilize the neighbor embedding algorithm to estimate the relationship between the LR and HR image pairs. To fully exploit the similarities across various scales inside the input LR image, we accumulate the previous resultant images as training examples for the subsequent reconstruction processes and adopt a gradual magnification scheme to upscale the LR input to the desired size step by step. In addition, to preserve sharper edges and suppress aliasing artifacts, we further apply the nonlocal means method to learn the similarity within the same scale and formulate a nonlocal prior regularization term to well pose SR estimation under a reconstruction-based SR framework. Experimental results demonstrate that the proposed method can produce compelling SR recovery both quantitatively and perceptually in comparison with other state-of-the-art baselines.

The continuous development of thermographic technology has led to the overall improvement of instruments used in medicine, surveillance, or military systems. However, thermographic imaging cameras still have a high cost compared to other alternatives on the market, such as visible light cameras and a much lower spatial resolution. Super-resolution is a technique that improves the visual quality of an image through software processing. This work studies three neural networks architectures based on deep learning capable of performing super-resolution of RGB images at x2 and x4 scales: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (SRGAN), Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR), and Wide Activation for Efficient and Accurate Image Super-Resolution (WDSR). These architectures, in this work, have been trained as a super-resolution system using thermographic images as input data. The evaluation was carried out using thermographic images from different thermographic cameras. The performance assessment was carried out using the Peak Signal to Noise Ratio (PSNR) and the Structural Similarity Index Measure (SSIM). In addition, low-resolution images from a low-cost thermographic camera were used as input to the neural networks to study the feasibility of this method.

Single Image Super-Resolution (SISR) using Convolutional Neural Networks (CNNs) for many applications in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">supervised</i> manner has resulted in state-of-the-art results. Such supervised models achieve remarkable accuracy; albeit their poor generalization ability for real-world Low-Resolution (LR) images. Supervised training in many SR works involves synthetically generated LR images from its corresponding High-Resolution (HR) images. As the distribution of such LR observation is relatively different from that of real LR image, the supervised training in SISR task results degradation when applied on real-world data. SISR has been scaled to real-world data recently by posing the unsupervised problem into a supervised one through learning the distribution of noisy LR observation first, following which supervised training is performed to obtain the SR image. It therefore involves two steps where the accuracy of SR image relies on how closely the LR’s distribution is learnt in the first step. In this work, we overcome such limitation by introducing unsupervised denoising network to transform real noisy LR image to clean image and then pre-trained SR network is utilised to increase the spatial resolution of cleaned LR image to generate SR image. Thus, instead of evaluating the denoised image in LR space to train the denoising network, we inspect the denoised image in SR space which allows to overcome the SR network’s generalization problem. The proposed Unsupervised Denoising framework for Super-Resolution ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">UDSR</i> ) is validated on real-world datasets (NTIRE-2020 Real-World SR Challenge validation and testing dataset (Track-1)) by comparing it with many recent unsupervised SISR methods. The performance of denoising and SR networks is superior in terms of various perceptual indices such as Perceptual Index (PI) and Ma Score in addition to numerous non-references metrics.

This paper proposes an unsupervised single-image Super-Resolution(SR) model using cycleGAN and domain discriminator to solve the problem of SR with unknown degradation using unpaired dataset. In previous approaches, paired dataset is required for training with assumed levels of image degradation. In real world SR applications, however, training sets are typically not of low and high resolution image pairs, but only low resolution images with unknown degradation are provided as inputs. To address the problem, we introduce a cycle-in-cycle GAN based unsupervised learning model using an unpaired dataset. In addition, we combine several losses attributed to image contents, such as pixel-wise loss, VGG feature loss and SSIM loss, for stable learning and performance improvement. We also propose a domain discriminator, which consists of noise discriminator, texture discriminator and color discriminator, to guide generated images to follow target domain distribution rather than source domain. We validate effectiveness of our model in quantitative and qualitative experiments using NTIRE2020 real-world SR challenge dataset.