Limitations when improving security camera video

This study explored the integration of super-resolution (SR) image reconstruction technology into environmental art design, addressing key challenges and highlighting its potential to enhance visual quality, design efficiency, ecological awareness, user satisfaction, and cultural heritage preservation. By examining the principles and models of SR technology, the study demonstrated its ability to significantly improve the aesthetic and functional standards of environmental art, contributing to more sustainable and culturally rich designs. The analysis and practical applications presented underscored the significance of SR technology in advancing both technological and artistic progress. Future developments in SR technology promise to further transform environmental art design, creating more dynamic, sustainable, and visually compelling environments.

Super resolution is a technology that converts low-resolution images into high-resolution images, and super resolution technologies using deep learning have recently been studied. The SRCNN model was first studied as a deep learning-based super-resolution technology, and the SRCNN model performs early up-sampling and learning using interpolation to perform super-resolution. In this paper, the best performance early up-sampling interpolation was investigated through the performance comparison of the early up-sampling method. Through this, it was found that the bicubic interpolation method derived good performance from up to 35% to at least 17% compared to other interpolation methods.

During the process of imagery, the factors including the motion between earth and the platform, atmosphere disturbance, out of focus, non-ideal sampling and so on, all can make the images blurred and degraded. Super resolution technology is the signal processing based method which can detect and remove the blur caused by the imaging system as well as recover spatial frequency information. Super resolution imaging processes one or more low resolution images acquired from the same scene to produce a single higher resolution image with more details.

With the extensive application of images in fields such as security surveillance, medical imaging, and satellite remote sensing, the issue of low resolution has become increasingly prominent. Super-resolution technology can reconstruct low-resolution images into high-resolution ones, thereby enhancing clarity and quality. However, existing methods still have shortcomings in detail restoration and edge enhancement. To address this, this paper introduces a sharpening module into the deep learning-based NinaSR super-resolution model to enhance edges and texture details. Experimental results show that this method effectively improves image sharpness and clarity while maintaining the overall structure, with a PSNR increase of approximately 0.038 dB compared to the original model. Additionally, it demonstrates a faster convergence speed in the early training stage, providing a new approach for high-resolution image reconstruction.

Multiplexed Superresolution CRISPR Imaging of Chromatin in Living Cells

Learning-based methods have been becoming the mainstream of single image super resolution (SR) technologies. It is effective to generate a high-resolution image from a single low resolution input. However, the quality of training data and the computational demand are two main problems. We propose a novel process framework for single image SR tasks aiming at these two problems, which consists of blur kernel estimation (BKE) and dictionary learning. BKE is utilized for improving the quality of training samples and compatibility between training samples and test samples, which is realized by minimizing the dissimilarity between cross-scale patches iteratively (intuitively be equivalent to maximizing the similarity of cross-scale patches). A selective patch processing (SPP) strategy is adopted in BKE and sparse recovery to reduce the number of patches needed to be processed. The fact that nature images usually contain continuity and discontinuity simultaneously ensures the feasibility of SPP. The experimental results show that our method produces more precise estimation for blurring kernel and better SR effect than several state-of-the-art SR algorithms on equal conditions, but needs much less computation time.

In this paper, we propose a novel single image super-resolution (SR) method based on low-rank sparse representation with self-similarity learning. Sparse representation is known as a promising method for SR. However, the sparse codes for low resolution (LR) patches gained by conventional method are not faithful to those for the original high resolution (HR) ones. To overcome this defect, we explore the structures of sparse representation for nonlocal similar patches in natural images by low-rank strategy. It assumes that the sparse codes for nonlocal similar patches should be low-rank. By low-rank constraint, similar components of sparse codes are shared and coding noises are removed, which improves coding accuracy and SR performance. Furthermore, we utilize self-similarity learning framework to generate a self-examples dictionary compatible to the low-rank sparse representation based SR. Experimental results demonstrate that our proposed method can recover good SR results both quantitatively and perceptually.

Super-resolution microscopy can transform our understanding of nanoparticle-cell interactions. Here, we established a super-resolution imaging technology to visualize nanoparticle distributions inside mammalian cells. The cells were exposed to metallic nanoparticles and then embedded within different swellable hydrogels to enable quantitative three-dimensional (3D) imaging approaching electron-microscopy-like resolution using a standard light microscope. By exploiting the nanoparticles' light scattering properties, we demonstrated quantitative label-free imaging of intracellular nanoparticles with ultrastructural context. We confirmed the compatibility of two expansion microscopy protocols, protein retention and pan-expansion microscopy, with nanoparticle uptake studies. We validated relative differences between nanoparticle cellular accumulation for various surface modifications using mass spectrometry and determined the intracellular nanoparticle spatial distribution in 3D for entire single cells. This super-resolution imaging platform technology may be broadly used to understand the nanoparticle intracellular fate in fundamental and applied studies to potentially inform the engineering of safer and more effective nanomedicines.

An approach for improving the z-axis resolution of MRI using super resolution (SR) technology in the post processing step is proposed. The 2D multi-slice MRI is often anisotropic, the z-resolution lower than the in plane resolution. And the isotropic is necessary for certain diagnostic while the truly isotropic image is hardly obtained. In this case the super resolution is an efficiency post-processing approach to obtain the demand image. In this method, the imaging volume is acquired multiple times with small spatial shifts in z-axis. We use an algorithm which introduces the Papoulis-Gerchberg extrapolation within the Iterative back-projection method to process the shift image serials. Experiments demonstrate that better edge definition in the slice select direction and signal to noise efficiency are obtained.

Remote sensing images are becoming increasingly widespread in military, earth resource exploration. Because of the limitation of a single sensor, we can obtain high spatial resolution grayscale panchromatic (PAN) images and low spatial resolution color multispectral (MS) images. Therefore, an important issue is to obtain a color image with high spatial resolution when there is only a PAN image at the input. The existing methods improve spatial resolution using super-resolution (SR) technology and spectral recovery using colorization technology. However, the SR technique cannot improve the spectral resolution, and the colorization technique cannot improve the spatial resolution. Moreover, the pansharpening method needs two registered inputs and can not achieve SR. As a result, an integrated approach is expected. We designed a novel multi-function model (MFmamba) to realize the tasks of SR, spectral recovery, joint SR and spectral recovery through three different inputs. Firstly, MFmamba utilizes UNet++ as the backbone, and a Mamba Upsample Block (MUB) is combined with UNet++. Secondly, a Dual Pool Attention (DPA) is designed to replace the skip connection in UNet++. Finally, a Multi-scale Hybrid Cross Block (MHCB) is proposed for initial feature extraction. Many experiments show that MFmamba is competitive in evaluation metrics and visual results and performs well in the three tasks when only the input PAN image is used.

The high-resolution image is the prerequisite of information acquisition and precise analysis. Multi-frame super-resolution images reconstruction technologies are able to address many image degraded issues (caused by external shooting environment), such as detail information lost, blurred edges, and so forth. According to the nanoscale memristor, a Multi-channel Memristive Pulse Coupled Neural Network (MMPCNN) model is proposed. This model is able to simulate the adaptive-variable linking coefficient in pulse coupled neural network. Meanwhile, the proposed network is applied to the multi-frame super resolution reconstruction for fusing the registered low resolution images. Furthermore, the sparse coding based super resolution method is performed to improve the original high-resolution image. Finally, a series of computer experiments and the relevant subjective/objective analysis jointly illustrate the validity and effectiveness of the entire scheme.

In recent years, CNN has been used for single image super-resolution (SR) with its success of in the field of computer vision. However, in the recovery process, there are always some high-frequency components that cant be recovered from low-resolution images to high-resolution ones by using existing CNN-based methods. In this paper, we propose an image super-resolution method based on CNN, which uses a two-level residual learning network to learn residual components, i.e., high-frequency components. We use the Super-Resolution Convolutional Neural Network (SRCNN) as the network structure in each level so that our proposed method can achieve the high-resolution images with high-frequency components that cant be obtained by the existing methods. In addition, we analyze the proposed method with considering three kinds of residual learning networks, which are different in the structure and superimposed layers of the residual learning network. In the experiments, we investigate the performance of the proposed method with various residual learning networks and the effect of image super-resolution to image captioning task.

Abstract. Single image super resolution (SISR) technology has been attracted much attention from remote sensing community due to its proven potentials in remote sensing applications. Existing SISR techniques varying from conventional interpolation methods to different network architectures. Generative adversarial networks (GANs) are one of the latest network architectures proven a greater potential as a SISR method whereas least attention has been given by the remote sensing community. Several studies have already been carried out on this context. However, yet there is no generalized GAN based approach to super resolve remote sensing imageries. Therefore, this study investigated the potentials of enhanced super resolution generative adversarial (ESRGAN) model to super resolve very high to medium resolution images from high to coarse resolution images for remote sensing applications. Two models were trained and Worldview-3 (WV3) images used as for very high resolution images. Whereas, down sampled WV3 and Sentinel-2(S2) were used as low resolution counterparts. Model performances were qualitatively and quantitatively analysed using standard metrics such as PSNR, SSIM, UIQI, CC, SAM, SID. Evaluation results emphasised super resolved images were preserved the original quality of the satellite images to a greater extent while improving its ground resolution.

Face video super-resolution (FVSR) aims to use continuous low resolution (LR) video frames to reconstruct face and recover facial details under the premise of ensuring authenticity. The existing video super-resolution (VSR) technology usually uses inter-frame information to achieve better super-resolution (SR) performance. However, due to the complex temporal dependence between frames, as the number of input frames increases, the information cannot be fully utilized, and even wrong information is introduced, resulting in poor performance. In this work, we propose an alignment propagation network for accumulating facial prior information (FAPN). We design a neighborhood information coupling (NIC) module based on optical flow estimation and alignment, where the current frame, the adjacent frames and the SR results of the previous frame are locally fused. The coupled frames are sent to a unidirectional propagation (UP) structure for propagation. Meanwhile, in the UP structure, the facial prior information is filtered and accumulated in the face super-resolution cell (FSRC), and the high-dimensional hidden state is introduced to propagate effective temporal information between frames along the unidirectional structure. Extensive evaluations and comparisons validate the strengths of our approach, FAPN can accumulate more facial details while ensuring the authenticity of the face. And the experimental results demonstrated that the proposed framework achieves better performance on PSNR (up to 0.31 dB), SSIM (up to 0.15 dB) and face recognition accuracy (up to 1.99%) compared with state-of-the-art methods.

Nanoscale synapse organization and dysfunction in neurodevelopmental disorders