High-resolution Image Reconstruction Research Articles

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.

Blind Super-Resolution of 3D MRI via Unsupervised Domain Transformation.

High-resolution medical images can be effectively used for clinical diagnosis. However, the acquisition of high-resolution images is difficult and often limited by medical instruments. Super-resolution (SR) methods provide a solution, where high-resolution (HR) images can be reconstructed from low-resolution (LR) ones. Most of existing deep neural networks for 3D SR medical images trained in a non-blind process, where LR images are directly degraded from HR data via a pre-determined downscale method. Such approaches rely heavily on the assumed degradation model, resulting in inevitable deviations in real clinical practice. Blind super-resolution, as a more attractive research line for this field, aims to generate HR images from LR inputs containing unknown degradation. Towards generalizing SR models for diverse types of degradation, we propose a robust blind SR of 3D medical images in an unsupervised manner with domain correction and upscaling treatment. First, a CycleGAN-based architecture is implemented to generate the LR data from the source domain to the target one for domain correction. Then, an upscaling network is learned via pre-determined HR-LR couples for reconstruction. The proposed framework is able to automatically learn noisy and blurry correction kernels for unpaired 3D SR magnetic resonance images (MRI). Our method achieves better and more robust performances in reconstruction of HR images from LR MRI with multiple unknown degradation processes, and show its superiority to other state-of-the-art supervised models and cycle-consistency based methods, especially in severe distortion cases.

PILN: A posterior information learning network for blind reconstruction of lung CT images

Background and objective:Computer tomography (CT) imaging technology has played significant roles in the diagnosis and treatment of various lung diseases, but the degradations in CT images usually cause the loss of detailed structural information and interrupt the judgement from clinicians. Therefore, reconstructing noise-free, high-resolution CT images with sharp details from degraded ones is of great importance for the computer-assisted diagnosis (CAD) system. However, current image reconstruction methods suffer from unknown parameters of multiple degradations in actual clinical images.Methods:To solve these problems, we propose a unified framework, so called Posterior Information Learning Network (PILN), for blind reconstruction of lung CT images. The framework consists of two stages: Firstly, a noise level learning (NLL) network is proposed to quantify the Gaussian and artifact noise degradations into different levels. Inception-residual modules are designed to extract multi-scale deep features from the noisy image, and residual self-attention structures are proposed to refine deep features to essential representations of noise. Secondly, by taking the estimated noise levels as prior information, a cyclic collaborative super-resolution (CyCoSR) network is proposed to iteratively reconstruct the high-resolution CT image and estimate the blur kernel. Two convolutional modules are designed based on cross-attention transformer structure, named as Reconstructor and Parser. The high-resolution image is restored from the degraded image by the Reconstructor under the guidance of the predicted blur kernel, while the blur kernel is estimated by the Parser according to the reconstructed image and the degraded one. The NLL and CyCoSR networks are formulated as an end-to-end framework to handle multiple degradations simultaneously.Results:The proposed PILN is applied to the Cancer Imaging Archive (TCIA) dataset and the Lung Nodule Analysis 2016 Challenge (LUNA16) dataset to evaluate its ability in reconstructing lung CT images. Compared with the state-of-the-art image reconstruction algorithms, it can provide high-resolution images with less noise and sharper details with respect to quantitative benchmarks.Conclusions:Extensive experimental results demonstrate that our proposed PILN can achieve better performance on blind reconstruction of lung CT images, providing noise-free, detail-sharp and high-resolution images without knowing the parameters of multiple degradation sources.

Interfacial debonding detection for CFST structures using an ultrasonic phased array: Application to the Shenzhen SEG building

Concrete filled steel tube (CFST) structures have been widely applied to the construction of high-rise buildings and bridges. However, interfacial debonding defects generally occur due to deficient construction quality, concrete shrinkage, and other reasons. In this paper, an imaging-based approach using a designed ultrasonic phased array is proposed for the semi-quantitative characterization of interfacial debonding defects in CFST columns. A total focusing method (TFM) is employed for high-resolution image reconstruction from the full matrix capture (FMC) dataset acquired by the phased array. Based on the reflection coefficient of the steel–concrete interface in the imaging result, a criterion is proposed to evaluate the degree of debonding damage. The proposed approach is used to evaluate the debonding defects in the 16 CFST columns of the Shenzhen SEG Building, which experienced abnormal shaking on May 18–20, 2021. The accuracy of the proposed method is fully validated with 15 boreholes on the CFST columns. Then, ultrasonic phase array measurements were conducted along 34 circumferential rings on nine of the CFST columns. The results show that the comprehensive debonding rate is as high as 46.6%. It is concluded that the proposed ultrasonic phased array method can accurately detect and locate the debonding defects in CFST structures, and this method has a broad application prospect for non-destructive inspection in civil engineering.

Text Prior Guided Scene Text Image Super-resolution.

Scene text image super-resolution (STISR) aims to improve the resolution and visual quality of low-resolution (LR) scene text images, while simultaneously boost the performance of text recognition. However, most of the existing STISR methods regard text images as natural scene images, ignoring the categorical information of text. In this paper, we make an inspiring attempt to embed text recognition prior into STISR model. Specifically, we adopt the predicted character recognition probability sequence as the text prior, which can be obtained conveniently from a text recognition model. The text prior provides categorical guidance to recover high-resolution (HR) text images. On the other hand, the reconstructed HR image can refine the text prior in return. Finally, we present a multi-stage text prior guided super-resolution (TPGSR) framework for STISR. Our experiments on the benchmark TextZoom dataset show that TPGSR can not only effectively improve the visual quality of scene text images, but also significantly improve the text recognition accuracy over existing STISR methods. Our model trained on TextZoom also demonstrates certain generalization capability to the LR images in other datasets.

Enhancing Forward-Looking Image Resolution: Combining Low-Rank and Sparsity Priors

Compressed sensing (CS)-based imaging technology has attracted a lot of interest because it can enhance imaging resolution. Targets of interest for forward-looking imaging radar are typically few in comparison to the entire imaging region. This sparsity allows for the natural application of CS to the reconstruction of high-resolution forward-looking images. However, conventional CS-based imaging methods can only perform well when the signal-to-noise ratio (SNR) is high. Strong noise in radar imaging prevents the CS-based methods from producing excellent imaging results. Inspired by the low-rank property of the received radar target echo and the sparsity of the forward-looking image targets, we present a combined low-rank and sparse prior restricted model for forward-looking imaging with a multichannel array radar to overcome strong noise. To solve the low-rank joint sparse double prior constraint optimization problem, an augmented Lagrange multiplier (ALM) reconstruction method under the framework of the alternating direction multiplier method (ADMM) is proposed. Finally, the results of simulation and real measurement data indicate that our presented method is fairly effective at enhancing the azimuth resolution and robustness of forward-looking radar imaging in comparison to other current methods.

SCTANet: A Spatial Attention-Guided CNN-Transformer Aggregation Network for Deep Face Image Super-Resolution

Numerous CNN-based algorithms have been proposed to reconstruct high-quality face images. However, the inability of convolution operation to model long-distance relationships limits the performance of the CNN-based methods. Moreover, in the high-resolution (HR) image reconstruction stage, with the well decoded feature representations, more efficient architecture design can be explored to synthesize pixel-level image details. In this work, we propose a spatial attention-guided CNN-Transformer aggregation network (SCTANet) for face image super-resolution (FSR) tasks. The core component in the deep feature extraction stage is the Hybrid Attention Aggregation (HAA) block. The HAA block has two parallel paths, one for the Residual Spatial Attention (RSA) block, the other for the Multi-scale Patch embedding and Spatial-attention Masked Transformer (MPSMT) block. The HAA block combines the strengths of CNN and transformer to effectively exploit both local and global information. For the reconstruction stage, we propose to use the Sub-pixel MLP-based Upsampling (SMU) module instead of the conventional CNN architecture. The SMU module promotes the reconstruction of pixel-level image details and reduces computational complexity. Extensive experiments on both synthetic and real-world face datasets demonstrate the superiority of our proposed SCTANet over state-of-the-art methods.

Unsupervised 3D Reconstruction with Multi-Measure and High-Resolution Loss

Multi-view 3D reconstruction technology based on deep learning is developing rapidly. Unsupervised learning has become a research hotspot because it does not need ground truth labels. The current unsupervised method mainly uses 3DCNN to regularize the cost volume to regression image depth. This approach results in high memory requirements and long computing time. In this paper, we propose an end-to-end unsupervised multi-view 3D reconstruction network framework based on PatchMatch, Unsup_patchmatchnet. It dramatically reduces memory requirements and computing time. We propose a feature point consistency loss function. We incorporate various self-supervised signals such as photometric consistency loss and semantic consistency loss into the loss function. At the same time, we propose a high-resolution loss method. This improves the reconstruction of high-resolution images. The experiment proves that the memory usage of the network is reduced by 80% and the running time is reduced by more than 50% compared with the network using 3DCNN method. The overall error of reconstructed 3D point cloud is only 0.501 mm. It is superior to most current unsupervised multi-view 3D reconstruction networks. Then, we test on different data sets and verify that the network has good generalization.