Image Super-Resolution Reconstruction Based on Multi-scale Residual Learning

A novel image super-resolution algorithm based on multi-scale dense recursive fusion network

The topic of super-resolution image reconstruction has recently received considerable attention within the research area. Super-resolution image reconstruction methods attempt to create a single high-resolution image from a number of low-resolution images (or a video sequence). The Bayesian maximum a posteriori (MAP) estimation method is widely used for super-resolution image reconstruction. So far, existing super-resolution reconstruction methods are all confronted with the problem of slow convergence and expensive computation. To satisfy the requirement of real-time application, we propose a high-efficiency super-resolution reconstruction algorithm that solves two key bottlenecks in the multi-frame MAP framework. The first breakthrough is to select the Armijo rule to identify the step length instead of the exact line search. The second one is to approximately compute the gradient of the MAP objective function using analytic representation instead of numerical calculation. Experimental results show that the proposed algorithm is applicable to real-time super-resolution reconstruction of low-resolution image sequences.

Spatial resolution of image is a critical index of image quality, and also is an important parameter in the area of image application. However, there are many factors which can lower and degenerate the quality of images in the process of capturing images. An effective solution to this problem is the super-resolution image reconstruction, that means reconstructing a high resolution (HR) image from some low resolution (LR) images, and eliminating the additive noise and blur which is caused by the size of the detector and optical at the same time. In this paper,one of project of convex set method for reconstructing a super-resolution image from multiframe undersampling images is introduced.First,a very important factor-the model of the process of imaging in spatial domain iterative method for super-resolution image reconstruction is mentioned. Next the reconstruction model and its steps are introduced through introducing the theory of project of convex set method. At last, the technique is available by experiments. The result indicates the project of convex set method for super-resolution image reconstruction has preferable effect on multiframe undersampling remote sensing images, and the technique of super-resolution image reconstruction can used in lots of fields such as remote sensing, computer vision, public security, physic imaging and so on.

Aiming at the problems of texture distortion and fuzzy details in the existing image super-resolution reconstruction methods, a super-resolution reconstruction network based on multi-channel attention mechanism is proposed. The texture extraction module designs an extremely lightweight multi-channel attention module in the network structure. Combined with one-dimensional convolution, it realizes cross-channel information interaction, focusing on important feature information; The texture restoration module introduces dense remaining blocks to restore some high-frequency texture details, improve the model performance, and generate high-quality reconstructed images. The proposed network can not only effectively improve the visual effect of the image, but the results on the benchmark data set CUFED5 are similar to the classic super-resolution (SRCNN) reconstruction method based on convolutional neural network. The peak signal-to-noise ratio (PSNR) and structure are similar. Degrees (SSIM) increased by 1.76dB and 0.062 respectively. Experimental results show that the designed network can improve the accuracy of texture migration and can effectively improve the quality of the generated image.

Superresolution reconstruction (SRR) is an effective approach for improving spatial resolution of image, which need not change the original imaging system hardware. Among the SRR methods, jointly estimate image registration and superresolution can overcome the serve aliased between low resolution images. However, further studies are still necessary for choose appropriate prior mode for better preserving edge of image. Also it is important for the choice of adaptive regularization parameters in the SRR based on regularization/maximum a posteriori (MAP) method. In this paper, we propose a method for joint image registration and SRR method based on MAP framework. In the reconstruction, the initial high resolution image is firstly obtained by the shift-and-add method. Then, the edge-preserved MRF model is used to improve the reconstructed image quality. Moreover, adaptive regularization method is used in the SRR. Experimental results demonstrate our improved SRR method effective.

This paper proposed a superresolution (SR) reconstruction method by combining the cross-diamond-hexagonal search (CDHS) block-matching algorithm (BMA) and the simple block-wise motion vector selection (BWMVS) strategy to obtain stable and high quality reconstruction results. The experimental results showed that the reconstruction quality of CDHS BMA is comparable with full search BMA but the computation time is greatly reduced. The occlusion including a scene change that severely damages the quality of the reconstructed video sequence in SR is effectively removed through the incorporation of the BWMVS in our reconstruction method. The stability due to BWMVS was verified by the reconstruction results using the standard interpolations.

In this paper, we propose a new super resolution (SR) reconstruction method to handle license plate numbers of vehicles in real traffic videos. Recently, SR reconstruction shemes based on regularization have been demonstrated to be effective because SR reconstrction is an ill-posed problem. Working within this promising framework, the residual data (RD) term can be weighted according to the differences among the observed LR images in the SR reconstruction model. Moreover, L1 norm is used to measure the RD term in order to improve the robustness of our method. Experiments show the proposed method improves the subjective visual quality of the high resolution images.

Numerous studies have been performed to apply camera vision technologies in robot-based agriculture and smart farms. In particular, to obtain high accuracy, it is essential to procure high-resolution (HR) images, which requires a high-performance camera. However, due to high costs it is difficult to widely apply the camera in agricultural robots. To overcome this limitation, we propose contrast and normal channel attention network (CNCAN) for super-resolution reconstruction (SR), which is the first research for the accurate semantic segmentation of crops and weeds even with low-resolution (LR) images captured by low-cost and LR camera. Attention block and activation function that considers high frequency and contrast information of images are used in CNCAN, and the residual connection method is applied to improve the learning stability.As a result of experimenting with three open datasets, namely, Bonirob, rice seedling and weed, and crop/weed field image (CWFID) datasets, the mean intersection of union (MIOU) results of semantic segmentation for crops and weeds with SR images through CNCAN were 0.7685, 0.6346, and 0.6931 in the Bonirob, rice seedling and weed, and CWFID datasets, respectively, confirming higher accuracy than other state-of-the-art methods for SR.

Feedback attention network for cardiac magnetic resonance imaging super-resolution

The existing deep learning-based remote sensing image super-resolution (SR) reconstruction methods have some problems, such as insufficient feature extraction and detail loss. We propose an efficient and fast deep convolutional neural network (CNN) single-image SR model, which achieves relatively advanced reconstruction performance. The number of layers and filter layers of CNNs are completely optimized, and the computing cost is significantly reduced. The global and local features of the original image are extracted by multiscale features; then, contextual information is enhanced in the inference network, and the reconstruction is done in advance of the dimensionality reduction operation to reduce the computational effort. The reconstruction performance is further improved using skip connection network in the whole network to solve the inefficiency of information in the transmission process. The experimental results show that the algorithm is 0.32 to 4.38 dB higher than other algorithms in peak signal-to-noise ratio value, the structure similarity index measure value reaches 0.9618, and the reconstructed image extracts more features and is richer in details.

Recent studies have shown that the use of deep convolutional neural networks (CNNs) can improve the performance of single image super-resolution reconstruction (SISR) methods. However, the existing CNN-based SISR model ignores the multi-scale features and shallow and deep features of the image, resulting in relatively low image reconstruction performance. To address these issues, this paper proposes a new multi-scale fractal residual network (MSFRN) for image super-resolution. On the basis of residual learning, a multi-scale fractal residual block (MSFRB) is designed. This block uses convolution kernels of different sizes to extract image multi-scale features and uses multiple paths to extract and fuse image features of different depths. Then, the shallow features extracted at the shallow feature extraction stage and the local features output by all MSFRBs are used to perform global hierarchical feature fusion. Finally, through sub-pixel convolution, the fused global features are used to reconstruct high-resolution images from low-resolution images. The experimental results on the five standard benchmark datasets show that MSFRN improved subjective visual effects and objective image quality evaluation indicators, and is superior to other state-of-the-art SISR methods.

The resolution of remote-sensing images is directly related to the application value of data products. Due to differences in imaging characteristics between digital cameras and remote-sensing cameras, the existing network models cannot get the best super resolution (SR) results of satellite images. In response to the requirements of remote-sensing image production, we propose a single image super-resolution (SISR) reconstruction method for specific type of remote-sensing satellite. First, we measure and model the imaging degradation phenomenon of remote-sensing satellite, including the image blur and noise model. Then, high-quality aerial images are down-sampled and degraded to construct paired training image datasets. We chose the most popular Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) as the basic structure and optimized the number of Residual-in-Residual Dense Block (RRDB) modules to further improve the processing efficiency. Finally, we perform a series of quantitative measurements of the SR image results, including image interpretation capability, reconstruction accuracy, ground resolution distance, and data processing efficiency, using higher resolution remote-sensing images as the benchmark. The experimental results demonstrate that our proposed method has higher interpretation capability and reconstruction accuracy for the SR processing of specific type remote-sensing satellite. Our proposed method is evaluated within a real satellite image product, that demonstrated it has the capability of pipeline super-resolution processing of remote sensing data products.

Recently, whole slide imaging (WSI) has become the gold standard for the clinical diagnosis of various diseases. It not only strengthens the cooperation between the computer and pathologists, but also promotes the development of remote primary diagnosis. WSI usually uses 20x and 40x objective lens scanners to scan the slides. Compared with the low-magnification lens, the high-magnification lens could provide high-resolution (HR) images, while sacrificing the large field-of-view (FOV), large depth-of-field (DOF), and high scanning efficiency instead. In this paper, we propose an image super-resolution (SR) reconstruction method based on a deep residual network (DSN), which improves flexibility and recovers the effective information neglected by the conventional network. After experimental verification, our method achieves large FOV, high scanning efficiency, and HR images simultaneously for assisting the diagnosis of pathologists.

Social media network is inseparable from image recognition, and image super-resolution (SR) reconstruction plays an important role in image recognition. The changes of scale and geometry are rarely considered in the image super-resolution reconstruction based on deep learning over the years, we introduce a super-resolution reconstruction network based on deformable convolutional network. We replace the ordinary convolution with the deformable convolution to pretend the geometric deformation and extract abundant local features. The image super-resolution reconstruction is usually based on the conventional convolutional neural network (CNN). Most CNN-based SR models do not utilize the features of the original low resolution (LR) image as much as possible, resulting in lower performance. After introducing the idea of deformable convolution, though the complexity is increased, the recognition accuracy is obviously raised.

Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network