Kernel Modeling Super-Resolution on Real Low-Resolution Images

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.

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.

The image super-resolution algorithm can overcome the imaging system's hardware limitation and obtain higher resolution and clearer images. Existing super-resolution methods based on convolutional neural networks(CNN) can learn the mapping relationship between high-resolution(HR) and low-resolution(LR) images. However, when the reconstruction target is a face image, the reconstruction results often have problems that the face area is too smooth and lacks details. We propose a guided cascaded face super-resolution network, called guided cascaded super-resolution network (GCFSRnet). GCFSRnet takes the LR image and a high-quality guided image as inputs, and it consists of a pose deformation module and a super-resolution network. Firstly, the pose deformation module converts the guide image's posture into the same as the low-resolution face image based on 3D fitting and 3D morphable model (3DMM). Then, the LR image and the deformed guide image are used as input of the super-resolution network. The super-resolution networks are formed by a cascade of two layers of networks, which extract different features. During the reconstruction process, the guide image can provide real facial details and help generate subtle facial textures. The cascade structure of a super-resolution network can gradually extract features and restore different levels of image details. The experimental results on the CASIA Web Face and CelebA datasets show that the proposed method can generate facial images with clear outlines and rich details, which are superior to other state-of-the-art methods such as SRResNet, SRGAN, VDSR, DBPN, etc.

Blind super-resolution (SR) of blurry and noisy low-resolution (LR) images is still a challenging problem in single image super-resolution (SISR). The performance of most existing convolutional neural network (CNN)-based models is inevitably degraded when LR images are corrupted by both blur and noise. For those blind SR methods based on kernel estimation, accurate estimation is barely attained under complex degradations and this gives rise to poor-quality results. To address these problems, we propose a deep progressive network under a probabilistic framework and a novel up-sampling method for blind super-resolution with multiple degradations, which effectively utilizes image priors across scales. Experimental results show that the proposed method achieves promising performance on images with multiple degradations.

Streaming low bitrate while preserving high-quality video content is a crucial topic in multimedia and video surveillance. In this work, we explore the problem of spatially and temporally reconstructing high-resolution (HR) frames from a high frame-rate low-resolution (LR) sequence and a few temporally subsampled HR frames. The targeted problem is essentially different from the problems handled by typical super-resolution (SR) methods such as single-image SR and video SR, which attempt to reconstruct HR images using only LR images. To tackle the targeted problem, we propose a deep quality transfer network, based on the convolutional neural network (CNN), which consists of modules including generation and selection of HR pixel candidates, fusion with LR input, residual learning and bidirectional architecture. The proposed CNN model has real-time performance at inference stage. The empirical studies have verified the generality of the proposed CNN model showing significant quality gains for video enhancement.

Lightweight single image super-resolution with attentive residual refinement network

Image super-resolution (SR) can be seen as finding a nonlinear mapping between low-resolution (LR) image and high-resolution (HR) image. Convolutional neural networks (CNN) based image SR methods have achieved great success based on features extracted from pretrained networks. However, the previous works less consider multiscale features. In this paper, we propose a SR cascaded multi-column convolutional neural network (SRCMCN) to recover HR image by learning multi-scale features from the corresponding LR image. Compared to existing CNN based image SR methods, the proposed method directly takes the original LR image as input to learn the residual between interpolated LR image and corresponding HR image, which will reduce the computational cost of convolution due to the small input size. Besides, in order to achieve high-quality reconstruction, we optimize our networks using mean absolute error (MAE) loss function. Experimental results demonstrate that our proposed method outperforms several state-of-the-art image SR methods in terms of both reconstructed image quality and computational efficiency.

Multimodal alias, guided, image super-resolution (SR) refers to the reconstruction of a high-resolution (HR) version of a low-resolution (LR) image with the aid of an HR image from another image modality. Common approaches for the SR problem include analytical methods which are computationally expensive. Deep learning methods are capable of learning a nonlinear mapping between LR and HR images from data, delivering high reconstruction accuracy at a low-computational cost during inference; however, these methods do not incorporate any prior knowledge about the problem, with the neural network model behaving like a black box. In this paper, we formulate multimodal image SR as a coupled convolutional sparse coding problem. To solve the corresponding minimization problem, we adopt the Method of Multipliers (MM). We then design a convolutional neural network (CNN) that unfolds the obtained MM algorithm. The proposed CNN accepts as input the LR image from the main modality and the HR image from the guidance modality to reconstruct the desired HR image. Unlike existing deep learning methods, our CNN provides an efficient and structured way to fuse information at different stages of the network and achieves high reconstruction accuracy. We evaluate the performance of the proposed model for the super-resolution of multi-spectral images guided by their high resolution RGB counterparts.

Single image super-resolution using a deep encoder–decoder symmetrical network with iterative back projection

Image super-resolution (SR) is the process of restoration of high-resolution (HR) image from its degraded images/image. Exigency of high-quality images in different technical fields has led it to be one of the prominent research domains in the area of digital image processing. In SR process, image reconstruction from single low-resolution (LR) image is more onerous process than obtaining it from multi-LR images. Performance of single image SR (SISR) processes is increased by utilizing different image priors in form of regularization. Use of regularization in mathematical equation helps in better visualization and reconstruction of original HR image. Its implementation requires maneuver and is a very important part of the image reconstruction process. In this paper, an attempt has been made to classify the existing techniques based on the priors used. Types of image priors and regularization used so far in the field of SISR have been discussed in detailed, comprising the recent advancements in this area. It also consists of the problems and limitations of the existing image priors and regularizations.

Deep Learning image processing methods are gradually gaining popularity in a number of areas including medical imaging. Classification, segmentation, and denoising of images are some of the most demanded tasks. In this study, we aim at enhancing optic nerve head images obtained by Optical Coherence Tomography (OCT). However, instead of directly applying noise reduction techniques, we use multiple state-of-the-art image Super-Resolution (SR) methods. In SR, the low-resolution (LR) image is upsampled to match the size of the high-resolution (HR) image. With respect to image enhancement, the upsampled LR image can be considered as low quality, noisy image, and the HR image would be the desired enhanced version of it. We experimented with several image SR architectures, such as super-resolution Convolutional Neural Network (SRCNN), very deep Convolutional Network (VDSR), deeply recursive Convolutional Network (DRCN), and enhanced super-resolution Generative Adversarial Network (ESRGAN). Quantitatively, in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), the SRCNN, VDSR, and DRCN significantly improved the test images. Although the ERSGAN showed the worst PSNR and SSIM, qualitatively, it was the best one.

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.

Recently deep convolutional neural network (CNN) has made significant achievement in Single Image Super-Resolution (SISR). Most CNN-based SISR methods used the default L2 norm of the error. However, for Hyperspectral Image (HSI), this loss function may bring spectral inconsistencies. The main reason is that most methods did not pay much attention to spectral loss. To HSI, the loss function should capture not only spatial information but also spectral consistency. In this paper, a Multi-Losses Function Network (MLFN) simultaneously considering spatial and spectral information is proposed, and is composed of two parts: one is Concatenate Dense Residual Network (CDRN), and the other is Loss Network (LN). CDRN is an image reconstruction network which can utilize the hierarchical features extracted from the low-resolution image. LN includes pixel-wise spatial loss and spectral loss which drive the learning of the entire reconstruction model. The experimental results prove that the proposed MLFN can enhance spatial resolution with the consistency of the spectrum of HSI preserved.

Recent deep learning approaches in single image super-resolution (SISR) can generate high-definition textures for super-resolved (SR) images. However, they tend to hallucinate fake textures and even produce artifacts. An alternative to SISR, reference-based SR (RefSR) approaches use high-resolution (HR) reference (Ref) images to provide HR details that are missing in the low-resolution (LR) input image. We propose a novel framework that leverages existing SISR approaches and enhances them with RefSR. Specifically, we refine the output of SISR methods using neural texture transfer, where HR features are queried from the Ref images. The query is conducted by computing the similarity of textural and semantic features between the input image and the Ref images. The most similar HR features, patch-wise, to the LR image is used to augment the SR image through an augmentation network. In the case of dissimilar Ref images from the LR input image, we prevent performance degradation by including the similarity scores in the input features of the network. Furthermore, we use random texture patches during the training to condition our augmentation network to not always trust the queried texture features. Different from past RefSR approaches, our method can use arbitrary Ref images and its lower-bound performance is based on the SR image. We showcase that our method drastically improves the performance of the base SISR approach.

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.