High-resolution Image Reconstruction Research Articles

LMD: Faster Image Reconstruction with Latent Masking Diffusion

As a class of fruitful approaches, diffusion probabilistic models (DPMs) have shown excellent advantages in high-resolution image reconstruction. On the other hand, masked autoencoders (MAEs), as popular self-supervised vision learners, have demonstrated simpler and more effective image reconstruction and transfer capabilities on downstream tasks. However, they all require extremely high training costs, either due to inherent high temporal-dependence (i.e., excessively long diffusion steps) or due to artificially low spatial-dependence (i.e., human-formulated high mask ratio, such as 0.75). To the end, this paper presents LMD, a faster image reconstruction framework with Latent Masking Diffusion. First, we propose to project and reconstruct images in latent space through a pre-trained variational autoencoder, which is theoretically more efficient than in the pixel-based space. Then, we combine the advantages of MAEs and DPMs to design a progressive masking diffusion model, which gradually increases the masking proportion by three different schedulers and reconstructs the latent features from simple to difficult, without sequentially performing denoising diffusion as in DPMs or using fixed high masking ratio as in MAEs, so as to alleviate the high training time-consumption predicament. Our approach allows for learning high-capacity models and accelerate their training (by 3x or more) and barely reduces the original accuracy. Inference speed in downstream tasks also significantly outperforms the previous approaches.

An Improved NLCS Algorithm Based on Series Reversion and Elliptical Model Using Geosynchronous Spaceborne–Airborne UHF UWB Bistatic SAR for Oceanic Scene Imaging

Geosynchronous spaceborne–airborne (GEO-SA) ultra-high-frequency ultra-wideband bistatic synthetic aperture radar (UHF UWB BiSAR) provides high-precision images for marine and polar environments, which are pivotal in glacier monitoring and sea ice thickness measurement for polar ocean mapping and navigation. Contrasting with traditional high-frequency BiSAR, it faces unique challenges, such as the considerable spatial variability, significant range–azimuth coupling, and vast volumes of echo data, which impede high-resolution image reconstruction. This paper presents an improved bistatic nonlinear chirp scaling (NLCS) algorithm for imaging oceanic scenes with GEO-SA UHF UWB BiSAR. This methodology extends the two-dimensional (2-D) spectrum up to the sixth order via the method of series reversion (MSR) to meet accuracy demands and then employs an elliptical model to elucidate the alterations in the azimuth frequency modulation (FM) rate mismatch. Initially, the imaging geometry and signal model are introduced, and then a separation of bistatic slant ranges based on the configuration is proposed. In addition, during range processing, after eliminating linear range cell migration (RCM), the derivation process for the sixth-order 2-D spectrum is detailed and an improved filter is applied to correct the high-order RCM. Finally, during azimuth processing, the causes of the FM rate mismatch are analyzed, a cubic perturbation function derived from the elliptical model is used for FM rate equalization, and a unified sixth-order filter is applied to complete the azimuth compression. Experimental results with point targets and natural oceanic scenes validate the outstanding efficacy of the proposed NLCS algorithm, particularly in imaging quality enhancements for GEO-SA UHF UWB BiSAR.

Deep-learning-based super-resolution for accelerating chemical exchange saturation transfer MRI.

Chemical exchange saturation transfer (CEST) MRI is a molecular imaging tool that provides physiological information about tissues, making it an invaluable tool for disease diagnosis and guided treatment. Its clinical application requires the acquisition of high-resolution images capable of accurately identifying subtle regional changes in vivo, while simultaneously maintaining a high level of spectral resolution. However, the acquisition of such high-resolution images is time consuming, presenting a challenge for practical implementation in clinical settings. Among several techniques that have been explored to reduce the acquisition time in MRI, deep-learning-based super-resolution (DLSR) is a promising approach to address this problem due to its adaptability to any acquisition sequence and hardware. However, its translation to CEST MRI has been hindered by the lack of the large CEST datasets required for network development. Thus, we aim to develop a DLSR method, named DLSR-CEST, to reduce the acquisition time for CEST MRI by reconstructing high-resolution images from fast low-resolution acquisitions. This is achieved by first pretraining the DLSR-CEST on human brain T1w and T2w images to initialize the weights of the network and then training the network on very small human and mouse brain CEST datasetsto fine-tune the weights. Using the trained DLSR-CEST network, the reconstructed CEST source images exhibited improved spatial resolution in both peak signal-to-noise ratio and structural similarity index measure metrics at all downsampling factors (2-8). Moreover, amide CEST and relayed nuclear Overhauser effect maps extrapolated from the DLSR-CEST source images exhibited high spatial resolution and low normalized root mean square error, indicating a negligible loss in Z-spectrum information. Therefore, our DLSR-CEST demonstrated a robust reconstruction of high-resolution CEST source images from fast low-resolution acquisitions, thereby improving the spatial resolution and preserving most Z-spectrum information.

High resolution imaging of acoustic orbital angular momentum wave based on orthogonal matching tracking

The orbital angular momentum (OAM) wave has shown great potential for improving radar imaging and underwater communication performance due to its helical wavefront phase and infinite orthogonal modes. However, there are currently no known applications of this technology in underwater imaging. In this paper, we employed acoustic OAM wave for underwater imaging and established transceiver signal models using the uniform circular array. We concurrently achieved two-dimensional imaging of azimuth and elevation angles, which differs from radar imaging. We proposed a matching process for the echo signal in the modal domain, the OAM wave beam image's sidelobe decreased by 7.9 dB in the elevation direction and 6.1 dB in the azimuth direction compared to the plane wave, with the mainlobe decreased by 0.2° in the elevation direction and 0.4° in the azimuth direction. Furthermore, this paper introduced OAM wave high-resolution image reconstruction based on the orthogonal matching pursuit (OMP) algorithm. Finally, we implemented broadband acoustic OAM wave for underwater imaging and introduced an image reconstruction method based on the modal domain OMP algorithm. Simulation results demonstrate that the use of OAM wave in underwater imaging is feasible, and the proposed scheme can achieve high-resolution imaging.

The Construction of a Lattice Image and Dislocation Analysis in High-Resolution Characterizations Based on Diffraction Extinctions.

This paper introduces a method for high-resolution lattice image reconstruction and dislocation analysis based on diffraction extinction. The approach primarily involves locating extinction spots in the Fourier transform spectrum (reciprocal space) and constructing corresponding diffraction wave functions. By the coherent combination of diffraction and transmission waves, the lattice image of the extinction planes is reconstructed. This lattice image is then used for dislocation localization, enabling the observation and analysis of crystal planes that exhibit electron diffraction extinction effects and atomic jump arrangements during high-resolution transmission electron microscopy (HRTEM) characterization. Furthermore, due to the method's effectiveness in localizing dislocations, it offers a unique advantage when analyzing high-resolution images with relatively poor quality. The feasibility of this method is theoretically demonstrated in this paper. Additionally, the method was successfully applied to observed edge dislocations, such as 1/6[211-], 1/6[2-11-], and 1/2[01-1], which are not easily observable in conventional HRTEM characterization processes, in electro-deposited Cu thin films. The Burgers vectors were determined. Moreover, this paper also attempted to observe screw dislocations that are challenging to observe in high-resolution transmission electron microscopy. By shifting a pair of diffraction extinction spots and superimposing the reconstructed images before and after the shift, screw dislocations with a Burgers vector of 1/2[011-] were successfully observed in electro-deposited Cu thin films.

Single image super-resolution based on Bendlets analysis and structural dictionary learning

High-resolution biological tissue slice images provide opportunities for more precise observation and analysis of histopathological features. These images typically consist of enclosed contours, and Bendlets transform is an effective means to approximate such structures. In this study, we leverage Bendlet transform to incorporate multi-level image data, thereby establishing a multi-scale pyramid feature set. This approach aids in achieving a sparser representation of image textures and structures. We apply Bendlets transform to extract multi-frequency wavelet subband features and formulate structured dictionaries for both high and low resolutions based on these features. After creating these dictionaries, we compute sparse representation coefficients using the low-resolution dictionary and subsequently integrate them with the high-resolution dictionary to generate high-resolution subbands. Ultimately, through the process of inverse wavelet transformation, we completed the reconstruction of high-resolution images. This method not only significantly enhances the restoration of image details and clarity but also effectively preserves the overall structural characteristics of the original images.

Shadow Detection and Reconstruction of High-Resolution Remote Sensing Images in Mountainous and Hilly Environments

Shadow Detection and Reconstruction of High-Resolution Remote Sensing Images in Mountainous and Hilly Environments

Computed Tomography of Transcatheter Aortic Valve Replacement-Related Complications

Transcatheter aortic valve replacement (TAVR) has revolutionized the treatment of severe aortic stenosis, with an impressive reduction in mortality and complication rates over the last decade, becoming a safer alternative in patients at high/moderate risk for surgical treatment. Complications are rare but can be life-threatening; thus, cardiac imagers must be familiar with their imaging findings. TAVR-related complications often require multimodality imaging, although ECG-gated cardiac computed tomography (CCT) is the technique of choice, given its high spatial resolution and multiplanar image reconstruction. This review will discuss the imaging findings of the most important post-TAVR complications and novel preventive measures.

ProxNF: Neural Field Proximal Training for High-Resolution 4D Dynamic Image Reconstruction

ProxNF: Neural Field Proximal Training for High-Resolution 4D Dynamic Image Reconstruction

Feature Pyramid Fusion Network for Hyperspectral Pansharpening.

Hyperspectral (HS) pansharpening aims at fusing an observed HS image with a panchromatic (PAN) image, to produce an image with the high spectral resolution of the former and the high spatial resolution of the latter. Most of the existing convolutional neural networks (CNNs)-based pansharpening methods reconstruct the desired high-resolution image from the encoded low-resolution (LR) representation. However, the encoded LR representation captures semantic information of the image and is inadequate in reconstructing fine details. How to effectively extract high-resolution and LR representations for high-resolution image reconstruction is the main objective of this article. In this article, we propose a feature pyramid fusion network (FPFNet) for pansharpening, which permits the network to extract multiresolution representations from PAN and HS images in two branches. The PAN branch starts from the high-resolution stream that maintains the spatial resolution of the PAN image and gradually adds LR streams in parallel. The structure of the HS branch remains highly consistent with that of the PAN branch, but starts with the LR stream and gradually adds high-resolution streams. The representations with corresponding resolutions of PAN and HS branches are fused and gradually upsampled in a coarse to fine manner to reconstruct the high-resolution HS image. Experimental results on three datasets demonstrate the significant superiority of the proposed FPFNet over the state-of-the-art methods in terms of both qualitative and quantitative comparisons.

A High-Resolution Image Reconstruction Method of Lung Nodules With B-Spline-Based Whale Optimization Algorithm (B-WOA) for Electrical Impedance Tomography

A High-Resolution Image Reconstruction Method of Lung Nodules With B-Spline-Based Whale Optimization Algorithm (B-WOA) for Electrical Impedance Tomography

Retracted: Application of High-Resolution Face Recognition and EDF Image Reconstruction in English Classroom Teaching

Retracted: Application of High-Resolution Face Recognition and EDF Image Reconstruction in English Classroom Teaching

An algorithm of unordered wavefront propagation in terahertz phase retrieval with dense multiplane data acquisition

Iterative phase retrieval algorithms from multiple diffraction patterns in the terahertz (THz) frequency range are a promising tool of computational imaging capable of providing high spatial resolution of reconstructed phase images. One of the commonly used algorithms is SBMIR, which employs multiple intensity distributions of the diffraction object wavefield as input data. Compared with single-frame methods, the multi-plane approach allows for a faster convergence, but requires time-consuming data acquisition from a receiver positioned at a variety of distances from the object. Previously, we proposed a method for THz data acquisition in a single scan mode, which allows one to quickly obtain an exhaustive set of diffraction distributions. In this paper we evaluate an up-to-date phase retrieval algorithm based on the SBMIR/R-SBMIR method (which utilizes stochastic wavefront propagation) on the experimental data captured by a single-scan technique. Unlike a number of conventional phase retrieval algorithms, which may require a series of numerical experiments for determining optimal intensity distributions from a large dataset, disordered propagation of the estimation wavefront guarantees the high-contrast and high-resolution image reconstruction without pre-setting the parameters. It is shown that the package use of the single-scan technique with the subsequent data processing using the R-SBMIR algorithm has application potential for automation of the multi-plane phase retrieval in the THz range.

A Review of GAN-Based Super-Resolution Reconstruction for Optical Remote Sensing Images

High-resolution images have a wide range of applications in image compression, remote sensing, medical imaging, public safety, and other fields. The primary objective of super-resolution reconstruction of images is to reconstruct a given low-resolution image into a corresponding high-resolution image by a specific algorithm. With the emergence and swift advancement of generative adversarial networks (GANs), image super-resolution reconstruction is experiencing a new era of progress. Unfortunately, there has been a lack of comprehensive efforts to bring together the advancements made in the field of super-resolution reconstruction using generative adversarial networks. Hence, this paper presents a comprehensive overview of the super-resolution image reconstruction technique that utilizes generative adversarial networks. Initially, we examine the operational principles of generative adversarial networks, followed by an overview of the relevant research and background information on reconstructing remote sensing images through super-resolution techniques. Next, we discuss significant research on generative adversarial networks in high-resolution image reconstruction. We cover various aspects, such as datasets, evaluation criteria, and conventional models used for image reconstruction. Subsequently, the super-resolution reconstruction models based on generative adversarial networks are categorized based on whether the kernel blurring function is recognized and utilized during training. We provide a brief overview of the utilization of generative adversarial network models in analyzing remote sensing imagery. In conclusion, we present a prospective analysis of forthcoming research directions pertaining to super-resolution reconstruction methods that rely on generative adversarial networks.

High-resolution face recognition and EDF image reconstruction application in English classroom teaching

High-resolution face recognition and EDF image reconstruction application in English classroom teaching

An optimized method for variational autoencoders based on Gaussian cloud model

Variational Autoencoders is one of the most valuable generative models in the field of unsupervised learning. Due to its own construction characteristics, Variational Autoencoders has insufficient precision for high-resolution image reconstruction. In this paper, the priori variant model of Variational Autoencoders based on the Gaussian Cloud Model is proposed to optimize the sampling method of latent variables, network structure and loss function. First, the Gaussian Cloud Model is used to replace the prior distribution of Variational Autoencoders. Second, the sampling process is changed into two consecutive Gaussian distributions. Finally, a new loss function based on the envelope curve of the Gaussian Cloud Model is presented for approximating the real data distribution. The method is evaluated qualitatively and quantitatively on several datasets to fully demonstrate the correctness and effectiveness of the method.

Gradient-Based Graph Attention for Scene Text Image Super-resolution

Scene text image super-resolution (STISR) in the wild has been shown to be beneficial to support improved vision-based text recognition from low-resolution imagery. An intuitive way to enhance STISR performance is to explore the well-structured and repetitive layout characteristics of text and exploit these as prior knowledge to guide model convergence. In this paper, we propose a novel gradient-based graph attention method to embed patch-wise text layout contexts into image feature representations for high-resolution text image reconstruction in an implicit and elegant manner. We introduce a non-local group-wise attention module to extract text features which are then enhanced by a cascaded channel attention module and a novel gradient-based graph attention module in order to obtain more effective representations by exploring correlations of regional and local patch-wise text layout properties. Extensive experiments on the benchmark TextZoom dataset convincingly demonstrate that our method supports excellent text recognition and outperforms the current state-of-the-art in STISR. The source code is available at https://github.com/xyzhu1/TSAN.

Single image super-resolution by cascading parallel-structure units through a deep-shallow CNN

Nowadays, single image super-resolution based on deep learning algorithms is reaching state-of-the-art performance. Nevertheless, most frameworks suffer from needing huge sample set and powerful computing hardware for training. Therefore, this paper presents Cascading Parallel-structure units through a Deep-Shallow (CPDS) CNN which provides satisfactory results not only with small sample set but also low computational cost with the goal of fully using the network design capabilities. In the proposed deep-shallow CNN, an approximated image is reconstructed via the lightweight shallow network, and the missing high-frequency details are retrieved by its complementary deep network. Regarding this, deep CNN is designed based on cascading parallel-structure units in the whole parts of the model to reduce the depth of the model and the number of network parameters. Besides, in the proposed cascading strategy, feature disappearance is restricted by concatenating and fusing features. Based on the parallel-structure of deep CNN, the initial features are firstly extracted using two parallel feature extractor units. Moreover, deep CNN applies a multi-scale fashion to detect and extract coarse-to-fine features simultaneously. Finally, the strategy of combining upsampling methods of deconvolution layer and pixelshuffle is adopted to ensure the high-resolution image reconstruction is accurately validated. Experimental results demonstrate the proposed end-to-end approach outperforms most state-of-the-art methods in terms of training specifications, evaluation metrics, and visual performance.

Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation

Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life images make it difficult to solve this problem using naïve deep learning approaches, where models are often trained on synthetically generated image pairs. Most of the effort so far has been focused on solving the inverse problem under some constraints, such as for a limited space of blur kernels and/or assuming noise-free input images. Yet, there is a gap in the literature to provide a well-generalized deep learning-based solution that performs well on images with unknown and highly complex degradations. In this paper, we propose IKR-Net (Iterative Kernel Reconstruction Network) for blind SISR. In the proposed approach, kernel and noise estimation and high-resolution image reconstruction are carried out iteratively using dedicated deep models. The iterative refinement provides significant improvement in both the reconstructed image and the estimated blur kernel even for noisy inputs. IKR-Net provides a generalized solution that can handle any type of blur and level of noise in the input low-resolution image. IKR-Net achieves state-of-the-art results in blind SISR, especially for noisy images with motion blur.

Studies Advanced in Image Super-resolution Reconstruction based on Deep Learning

Image super-resolution reconstruction (SR) has always been a research hotspot in the computer vision community, whose purpose is to convert low-resolution (LR) images into high-resolution (HR) images by algorithms without changing the hardware. Early SR works were mainly based on manual features and mathematical statistical models, relying on interpolation to achieve high-resolution image reconstruction. Thanks to the rapid development of convolutional neural networks, SR based on deep learning has achieved breakthroughs in both accuracy and speed. This paper first introduces the basic principles of image super-resolution reconstruction, including the basic framework and loss function of SR. Then, we introduce the representative super-resolution reconstruction methods such as SRCNN, SRGAN, and TTSR. We also introduce the common public datasets and evaluation indexes, and compare the performance of several SR methods to analyze their advantages and disadvantages. Finally, we summarize the existing challenges in the image super-resolution reconstruction, and give a look out for the future development direction of SR.