A fast approach for edge preserving super-resolution

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.

Deep Feature Blend Attention: A New Frontier in Super Resolution Image Generation

Rendering high-resolution (HR) graphics brings substantial computational costs. Efficient graphics super-resolution (SR) methods may achieve HR rendering with small computing resources and have attracted extensive research interests in industry and research communities. We present a new method for real-time SR for computer graphics, namely Super-Resolution by Predicting Offsets (SRPO). Our algorithm divides the image into two parts for processing, i.e., sharp edges and flatter areas. For edges, different from the previous SR methods that take the anti-aliased images as inputs, our proposed SRPO takes advantage of the characteristics of rasterized images to conduct SR on the rasterized images. To complement the residual between HR and low-resolution (LR) rasterized images, we train an ultra-efficient network to predict the offset maps to move the appropriate surrounding pixels to the new positions. For flat areas, we found simple interpolation methods can already generate reasonable output. We finally use a guided fusion operation to integrate the sharp edges generated by the network and flat areas by the interpolation method to get the final SR image. The proposed network only contains 8,434 parameters and can be accelerated by network quantization. Extensive experiments show that the proposed SRPO can achieve superior visual effects at a smaller computational cost than the existing state-of-the-art methods.

This paper proposes a new algorithm to integrate image registration into image super-resolution (SR). Image SR is a process to reconstruct a high-resolution (HR) image by fusing multiple low-resolution (LR) images. A critical step in image SR is accurate registration of the LR images or, in other words, effective estimation of motion parameters. Conventional SR algorithms assume either the estimated motion parameters by existing registration methods to be error-free or the motion parameters are known a priori. This assumption, however, is impractical in many applications, as most existing registration algorithms still experience various degrees of errors, and the motion parameters among the LR images are generally unknown a priori. In view of this, this paper presents a new framework that performs simultaneous image registration and HR image reconstruction. As opposed to other current methods that treat image registration and HR reconstruction as disjoint processes, the new framework enables image registration and HR reconstruction to be estimated simultaneously and improved progressively. Further, unlike most algorithms that focus on the translational motion model, the proposed method adopts a more generic motion model that includes both translation as well as rotation. An iterative scheme is developed to solve the arising nonlinear least squares problem. Experimental results show that the proposed method is effective in performing image registration and SR for simulated as well as real-life images.

Image super-resolution is of great interest in medical imaging field. However, different from natural images studied in computer vision field, the low-resolution (LR) medical imaging data is often a stack of high-resolution (HR) 2D slices with large slice thickness. Consequently, the goal of super-resolution for medical imaging data is to reconstruct the missing slice(s) between any two consecutive slices. Since some modalities (e.g., T1-weighted MR image) are often acquired with high-resolution (HR) image, it is intuitive to harness the prior self-similarity information in the HR image for guiding the super-resolution of LR image (e.g., T2-weighted MR image). The conventional way is to find the profile of patchwise self-similarity in the HR image and then use it to reconstruct the missing information at the same location of LR image. However, the local morphological patterns could vary significantly across the LR and HR images, due to the use of different imaging protocols. Therefore, such direct (un-supervised) adaption of self-similarity profile from HR image is often not effective in revealing the actual information in the LR image. To this end, we propose to employ the existing image information in the LR image to supervise the estimation of self-similarity profile by requiring it not only being optimal in representing patches in the HR image, but also producing less reconstruction errors for the existing image information in the LR image. Moreover, to make the anatomical structures spatially consistent in the reconstructed image, we simultaneously estimate the self-similarity profiles for a stack of patches across consecutive slices by solving a group sparse patch representation problem. We have evaluated our proposed super-resolution method on both simulated brain MR images and real patient images with multiple sclerosis lesion, achieving promising results with more anatomical details and sharpness.

In this paper, we demonstrate simple algorithms that project low resolution (LR) images differing in subpixel shifts on a high resolution (HR) also called super resolution (SR) grid. The algorithms are very effective in accuracy as well as time efficiency. A number of spatial interpolation techniques using nearest neighbor, inverse-distance weighted averages, Radial Basis Functions (RBF) etc. are used in projection. For best accuracy of reconstructing SR image by a factor of two requires four LR images differing in four independent subpixel shifts. The algorithm has two steps: i) registration of low resolution images and (ii) shifting the low resolution images to align with reference image and projecting them on high resolution grid based on the shifts of each low resolution image using different interpolation techniques. Experiments are conducted by simulating low resolution images by subpixel shifts and subsampling of original high resolution image and the reconstructing the high resolution images from the simulated low resolution images. The results of accuracy of reconstruction are compared by using mean squared error measure between original high resolution image and reconstructed image. The algorithm was tested on remote sensing images and found to outperform previously proposed techniques such as Iterative Back Projection algorithm (IBP), Maximum Likelihood (ML) algorithms. The algorithms are robust and are not overly sensitive to the registration inaccuracies.

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.

Super-resolution (SR) reconstruction is a technique to yield a higher resolution (HR) image from aliasing low resolution (LR) ones. An LR image is upsampled as the initialization, and then iteratively corrected in comparison with the other LR images. As the solution satisfying the SR constraints is non-unique, it is impossible to recover the original HR details completely by SR techniques. The solution reconstructed is sensitive to the starting point, especially when LR observations are insufficient, and may converge to a local optimum point. SR images reconstructed with different initializations may diverge in different ways from the true HR image. The influence of the initial HR estimate has not been sufficiently addressed so far by existing SR methods. We will explore this initial image selection issue to improve the performance of SR reconstruction.

Multi-modal imaging requires image fusion to combine advantages of different types of sensors and requires super-resolution (SR) because of limited spatial resolution of source images. In this study, a novel framework is proposed for unification of image SR and the fusion process to obtain a high-resolution (HR)-fused image from a set of low-resolution (LR) multi-modal images. The jointly trained dictionaries of LR patches and corresponding HR patches are used for sparse representation of LR source image patches and HR-fused image patches, respectively. The sparse coefficients vectors for corresponding patches of source LR images are determined by using orthogonal matching pursuit and a local information content-based metric is employed to fuse these sparse coefficients. The corresponding HR-fused image patch is obtained by combining elements of the HR dictionary as per the fused coefficients of the LR image patches. The experimental results on sets of multi-modal images exhibited that the proposed method outperformed the existing fusion and SR techniques in terms of visual quality and image fusion quality metrics.

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.

Super-resolution (SR) techniques produce a high resolution (HR) image from a set of low-resolution (LR) undersampled images. Usually, SR problems are posed as estimation problems where the LR images are contaminated by stationary noise. However, in real SR problems is very common to have non-stationary noise due to problems in the registration of the images or outliers. SR methods that address this type of problems are called robust. In this paper we propose a novel robust SR method that employs a median filter directly in the data from the LR images, before proceeding to the interpolation and deblurring steps that are common in SR. We compare this new method with other robust SR methods with synthetic and real data, proving that it outperforms the other methods in both cases.KeywordsProjective MethodMedian FilterRegistration ErrorPepper NoiseIrregular SampleThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Acquiring degraded images with paired high-resolution (HR) images is often challenging, impeding the advance of image super-resolution in real-world applications. By generating realistic low-resolution (LR) images with degradation similar to that in real-world scenarios, simulated paired LR-HR data can be constructed for supervised training. However, most of the existing work ignores the degradation uncertainty of the generated realistic LR images, since only one LR image has been generated given an HR image. To address this weakness, we propose learning the degradation uncertainty of generated LR images and sampling multiple LR images from the learned LR image (mean) and degradation uncertainty (variance) and construct LR-HR pairs to train the super-resolution (SR) networks. Specifically, uncertainty can be learned by minimizing the proposed loss based on Kullback-Leibler (KL) divergence. Furthermore, the uncertainty in the feature domain is exploited by a novel perceptual loss; and we propose to calculate the adversarial loss from the gradient information in the SR stage for stable training performance and better visual quality. Experimental results on popular real-world datasets show that our proposed method has performed better than other unsupervised approaches.

Cross-Resolution Person Re-Identification (re-ID) aims to match images with disparate resolutions arising from variations in camera hardware and shooting distances. Most conventional works utilize Super-Resolution (SR) models to recover Low Resolution (LR) images to High Resolution (HR) images. However, because the SR models cannot completely compensate for the missing information in the LR images, there is still a large gap between the HR image recovered from the LR images and the real HR images. To tackle this challenge, we propose a novel Multi-Scale Image- and Feature-Level Alignment (MSIFLA) framework to align the images on multiple resolution scales at both the image and feature level. Specifically, (i) we design a Cascaded Multi-Scale Resolution Reconstruction (CMSR2) module, which is composed of three cascaded Image Reconstruction (IR) networks, and can continuously reconstruct multiple variables of different resolution scales from low to high for each image, regardless of image resolution. The reconstructed images with specific resolution scales are of similar distribution; therefore, the images are aligned on multiple resolution scales at the image level. (ii) We propose a Multi-Resolution Representation Learning (MR2L) module which consists of three-person re-ID networks to encourage the IR models to preserve the ID-discriminative information during training separately. Each re-ID network focuses on mining discriminative information from a specific scale without the disturbance from various resolutions. By matching the extracted features on three resolution scales, the images with different resolutions are also aligned at the feature-level. We conduct extensive experiments on multiple public cross-resolution person re-ID datasets to demonstrate the superiority of the proposed method. In addition, the generalization of MSIFLA in handling cross-resolution retrieval tasks is verified on the UAV vehicle dataset.

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.

Example-based super-resolution (SR) methods learn the correspondences between low resolution (LR) and high-resolution (HR) image patches, where the patches are extracted from a training database. To reconstruct a single LR image into a HR one, each LR image patch is processed by the previously trained model to recover its corresponding HR patch. For this reason, they are computationally inefficient. We propose the use of a selective patch processing technique to carry out the super-resolution step more efficiently, while maintaining the output quality. In this technique, only patches of high variance are processed by the costly reconstruction steps, while the rest of the patches are processed by fast bicubic interpolation. We have applied the proposed improvement on representative example-based SR methods to super-resolve text images. The results show a significant speed up for text SR without a drop in theocrat accuracy. In order to carry out an extensive and solid performance evaluation, we also present a public database of text images for training and testing example-based SR methods.