GSSTU: Generative Spatial Self-Attention Transformer Unit for Enhanced Video Prediction.

Traditional deblurring algorithms such as blur kernel estimation and gradient prior methods, these methods can only deal with a single type of blurry image, and such methods are very time-consuming. Due to the excellent performance of deep learning neural networks in the field of image generation, this paper regards the traditional image deblurring problem as a special image transformation problem. First, a multi-scale network is used to restore the blurry image, the network can restore the image in an end-to-end manner. Then, the multi-scale network will output a restored image. Finally, the generative adversarial network (GAN) can make the restored image closer to the real clear image in the sense. In terms of loss function, perceptual loss in content loss is adopted to ensure the consistency of the generated image and clear image in content. The results of deblurring will be evaluated by testing the peak signal to noise ratio (PSNR) and structural similarity (SSIM) between the generated image and the clear image. The results show that the PSNR and SSIM of the algorithm in the GoPro dataset have reached 28.01 and 0.8538, respectively, and can recover some details lost due to shake blur.

The ability of predicting future frames in video sequences, known as video prediction, is an appealing yet challenging task in computer vision. This task requires an in-depth representation of video sequences and a deep understanding of real-word causal rules. Existing approaches for tackling the video prediction problem can be classified into two categories: deterministic and stochastic methods. Deterministic methods lack the ability of generating possible future frames and often yield blurry predictions. On the other hand, although current stochastic approaches can predict possible future frames, their models lack the ability of action control in the sense that they cannot generate the desired future frames conditioned on a specific action. In this paper, we propose new generative adversarial networks (GANs) for stochastic video prediction. Our framework, called VPGAN, employs an adversarial inference model and a cycle-consistency loss function to empower the framework to obtain more accurate predictions. In addition, we incorporate a conformal mapping network structure into VPGAN to enable action control for generating desirable future frames. In this way, VPGAN is able to produce fake videos of an object moving along a specific direction. Experimental results show that a combination of VPGAN and pre-trained image segmentation models outperforms existing stochastic video prediction methods.

The ability of predicting future frames in video sequences, known as video prediction, is an appealing yet challenging task in computer vision. This task requires an in-depth representation of video sequences and a deep understanding of real-word causal rules. Existing approaches for tackling the video prediction problem can be classified into two categories: deterministic and stochastic methods. Deterministic methods lack the ability of generating possible future frames and often yield blurry predictions. On the other hand, although current stochastic approaches can predict possible future frames, their models lack the ability of action control in the sense that they cannot generate the desired future frames conditioned on a specific action. In this paper, we propose new generative adversarial networks (GANs) for stochastic video prediction. Our framework, called VPGAN, employs an adversarial inference model and a cycle-consistency loss function to empower the framework to obtain more accurate predictions. In addition, we incorporate a conformal mapping network structure into VPGAN to enable action control for generating desirable future frames. In this way, VPGAN is able to produce fake videos of an object moving along a specific direction. Experimental results show that the combination of VPGAN with a pre-trained image segmentation model outperforms existing stochastic video prediction methods.

Objective. Computed tomography (CT) and magnetic resonance imaging (MRI) are widely used in medical imaging modalities, and provide valuable information for clinical diagnosis and treatment. However, due to hardware limitations and radiation safety concerns, the acquired images are often limited in resolution. Super-resolution reconstruction (SR) techniques have been developed to enhance the resolution of CT and MRI slices, which can potentially improve diagnostic accuracy. To capture more useful feature information and reconstruct higher quality super-resolution images, we proposed a novel hybrid framework SR model based on generative adversarial networks. Approach. The proposed SR model combines frequency domain and perceptual loss functions, which can work in both frequency domain and image domain (spatial domain). The proposed SR model consists of 4 parts: (i) the discrete Fourier transform (DFT) operation transforms the image from the image domain to frequency domain; (ii) a complex residual U-net performs SR in the frequency domain; (iii) the inverse discrete Fourier transform (iDFT) operation based on data fusion transforms the image from the frequency domain to image domain; (iv) an enhanced residual U-net network is used for SR of image domain. Main results. Experimental results on bladder MRI slices, abdomen CT slices, and brain MRI slices show that the proposed SR model outperforms state-of-the-art SR methods in terms of visual quality and objective quality metric such as the structural similarity (SSIM) and the peak signal-to-noise ratio (PSNR), which proves that the proposed model has better generalization and robustness. (Bladder dataset: upscaling factor of 2: SSIM = 0.913, PSNR = 31.203; upscaling factor of 4: SSIM = 0.821, PSNR = 28.604. Abdomen dataset: upscaling factor of 2: SSIM = 0.929, PSNR = 32.594; upscaling factor of 4: SSIM = 0.834, PSNR = 27.050. Brain dataset: SSIM = 0.861, PSNR = 26.945). Significance. Our proposed SR model is capable of SR for CT and MRI slices. The SR results provide a reliable and effective foundation for clinical diagnosis and treatment.

The main purpose of abnormal power consumption detection for power users is to maintain the legitimate rights and interests of normal users, improve the economic benefits of power grid companies, and thereby reduce non-technical losses (NTL). In order to realize the rational use of user-side data and improve the efficiency of power audit, this article proposes an improved SVM power theft detection model based on decision tree. First of all, to address the problem of less electricity stealing data, this article combines convolutional neural networks (CNN) and generative adversarial networks (GAN) for data generation, and uses the powerful feature extraction function of CNN to extract the features of different stealing methods to guide GAN. Then the improved support vector machine (SVM) model based on decision tree (DT) detects user data. When classifying, it combines SVM and KNN for classification, which solves the point of SVM near the decision plane. For the problem of low classification accuracy, simulation experiments finally verified the effectiveness of the proposed model.

Day-ahead load forecasting belongs to short-term forecasting, which is the basis of new energy utilization as well as power system operation. The large-scale consumption of new energy and the uncertainty of the demand side bring new challenges to day-ahead load forecasting. Traditional recurrent neural networks have limitations in feature extraction capability and learning efficiency. In order to fully learn the features in the load data, we propose a model Patch-LSTM-MLP combining LSTM, patch technique and multilayer perceptron for day-ahead load forecasting. Patch-LSTM-MLP consists of two multilayer perceptron blocks and an LSTM model based on the novel patch technique. Specifically, the proposed model employs LSTM to capture the global temporal patterns of load sequences, and introduces local multilayer perceptron and variable multilayer perceptron to enhance the model's ability to capture local temporal patterns and correlations among variables. In this paper, two public load datasets are selected to validate the effectiveness of the proposed model, which provides new ideas for the application of recurrent networks in day-ahead load forecasting.

Brain tumors are formed due to the abnormal growth of the cells that get multiplied and become in uncontrollable perspective. Tumors can damage brain cells by pressing down the skull, which consociate begins in, which negatively affects human health. In advanced stages, a brain tumor is a more dangerous infection that cannot be relieved. Brain tumor detection and early prevention are necessary in today's world. An extreme learning machine (ELM) is a widely adopted algorithm in machine learning. It is proposed to use classification models in brain tumor imaging. This classification is based on the techniques implemented: Convolutional Neural Networks(CNN) and Generative Adversarial Networks(GAN). CNN efficiently solves the convex optimization problem and is faster, requiring less human effort. The algorithmic architecture of GAN uses two neural networks, pocking one against the other. These networks are implemented in various fields to classify brain Tumor images. The present study mainly aims to introduce a new proposed classification system of preschool children brain imaging with Hybrid Convolutional Neural Networks and with the techniques of GAN. The proposed technique is compared with the existing hybrid-CNN and hybrid-GAN techniques. The outcomes are encouraging because the loss is deduced, and the accuracy facet increases. The proposed system achieved a training accuracy of 97.8% and a validation accuracy of 89%. The outcomes of the studies show that ELM in the platform of GAN for preschool children brain imaging classification has achieved higher predictive performance than the traditional classification mechanisms in increasingly complex scenarios. Time elapsed for training brain images samples finds inference value for training samples and time elapsed value increased by 28.9855%. Approximation ratio for cost based on probability, finding Approximation ratio for low probability range is increased by 88.1%. The combination of CNN, GAN and hybrid-CNN, hybrid-GAN, and hybrid CNN + GAN, compared with the proposed hybrid system, increased Detection latency for low range learning rate by 3.31%.

Industrial robotic manipulators are prone to surface wear and damage, leading to unexpected failures and costly downtimes. Early detection of such defects is crucial for enabling predictive maintenance. This study proposes a vision‐based pattern recognition framework that combines convolutional neural networks (CNN) and generative adversarial networks (GANs) to enhance defect detection and tool failure prediction in IoRT‐connected environments. The proposed scheme leverages CNN to extract multi‐scale visual features from raw images of industrial machine components. Convolutional layers are stacked with varying filter sizes to capture fine‐grained surface defects and broader contextual patterns. The pooling layers selectively retain discriminative activations, producing feature embeddings that highlight characteristics such as pitting, scratches, and cracks. This structure allows the network to transform raw pixels into meaningful patterns for reliable classification. To address data scarcity and improve generalisation, the GAN component generates synthetic defect images by simulating real‐world variability, including defect shape, background textures and orientation. The adversarial training between the generator and discriminator enhances the realism and diversity of augmented data, which in turn improves the CNN's robustness. Applied to ball screw drive spindle images, the integrated CNN‐GAN model achieves 96.7% classification accuracy, with 94% precision, 92% recall and 93% AUC. These results support the system's suitability for predictive maintenance and real‐time deployment in smart industrial settings.

Image stitching is a fundamental task in computer vision, enabling critical applications such as panoramic imaging, augmented reality (AR), and autonomous perception systems. However, existing stitching algorithms exhibit significant performance variations under real-world challenges–including illumination changes, noise interference, and geometric distortions–making reliable quality assessment difficult. To address this challenge, we introduce StitchEval, a comprehensive benchmark framework incorporating both objective and subjective assessment metrics, including structural similarity (SSIM), mean squared error (MSE), peak signal-to-noise ratio (PSNR) and human-rated subjective scores (SS). Additionally, we integrate a human-perception-based scoring system to enhance the comprehensiveness of the evaluation. By applying illumination transformations, noise interference, and geometric variations to the original dataset, we systematically analyze the robustness of different stitching algorithms. Furthermore, the proposed evaluation framework and dataset construction methodology are designed to be highly flexible, allowing seamless integration with other datasets to facilitate cross-dataset comparisons and broader benchmarking of stitching algorithms. The insights derived from this study provide a valuable reference for optimizing future stitching methods and improving algorithm adaptability in real-world scenarios.

It is difficult for laser scanning confocal microscopy to obtain high- or ultra-high-resolution laser confocal images directly, which affects the deep mining and use of the embedded information in laser confocal images and forms a technical bottleneck in the in-depth exploration of the microscopic physiological and biochemical processes of plants. The super-resolution reconstruction model (SRGAN), which is based on a generative adversarial network and super-resolution reconstruction model (SRResNet), which is based on a residual network, was used to obtain single and secondary super-resolution reconstruction images of laser confocal images of the root cells of the hyperaccumulator Solanum nigrum. Using the peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and mean opinion score (MOS), the models were evaluated by the image effects after reconstruction and were applied to the recognition of endocytic vesicles in Solanum nigrum root cells. The results showed that the single reconstruction and the secondary reconstruction of SRGAN and SRResNet improved the resolution of laser confocal images. PSNR, SSIM, and MOS were clearly improved, with a maximum PSNR of 47.690. The maximum increment of PSNR and SSIM of the secondary reconstruction images reached 21.7% and 2.8%, respectively, and the objective evaluation of the image quality was good. However, overall MOS was less than that of the single reconstruction, the perceptual quality was weakened, and the time cost was more than 130 times greater. The reconstruction effect of SRResNet was better than that of SRGAN. When SRGAN and SRResNet were used for the recognition of endocytic vesicles in Solanum nigrum root cells, the clarity of the reconstructed images was obviously improved, the boundary of the endocytic vesicles was clearer, and the number of identified endocytic vesicles increased from 6 to 9 and 10, respectively, and the mean fluorescence intensity was enhanced by 14.4% and 7.8%, respectively. Relevant research and achievements are of great significance for promoting the application of deep learning methods and image super-resolution reconstruction technology in laser confocal image studies.

As the need for high-quality video increases it has become necessary to develop smarter compression methods. Artificial neural networks (ANNs) have emerged as an effective tool in this field enabling them to extract the most important features from video and minimize temporal and spatial redundancy resulting in an efficient and high-quality compressed representation. Some of the most prominent models used are: Hybrid neural networks (CNN+RNN(LSTM)) Hybrid neural networks combine convolutional neural networks (CNNs), recurrent neural networks (RNNs), and especially long short-term memory (LSTM) units to extract spatial and temporal features from data, GAN, GANs compress video files while maintaining high perceptual quality. They encode each frame into a compressed latent representation, allowing for realistic reconstruction. This method is efficient, making it ideal for video transmission applications where perceptual accuracy is more important than perfect pixel accuracy. These techniques enable efficient compression without significant quality loss, representing a paradigm shift in modern video compression techniques. After analyzing the results the highest compression ratio (94.75) was achieved by compressing using the GAN algorithm. The highest PSNR (36.08) was achieved by CNN+RNN(LSTM) compression.

Accurate retinal vessel segmentation plays a vital role in the early detection and diagnosis of ophthalmologic dis- eases such as diabetic retinopathy, glaucoma, and hypertension. Traditional image processing and machine learning techniques often struggle to capture the fine vessel structures and complex variations present in retinal fundus images. To overcome these limitations, this study proposes a hybrid deep learning framework that combines Convolutional Neural Networks (CNNs) and Gen- erative Adversarial Networks (GANs) for precise retinal vessel segmentation. In the proposed method, the CNN component serves as the feature extractor, learning multi-scale spatial and contextual features from retinal images, while the GAN framework enhances segmentation accuracy by employing a discriminator network that distinguishes between real and generated vessel maps. This adversarial learning setup encourages the generator to produce vessel segmentations that closely resemble ground truth images. Additionally, preprocessing techniques such as contrast enhancement and noise reduction are applied to improve the visibility of retinal structures, and post-processing steps refine the vessel boundaries for higher accuracy. Experimental results on publicly available retinal image datasets, such as DRIVE and STARE, demonstrate that the pro- posed GAN-CNN model outperforms conventional CNN-based segmentation methods in terms of accuracy, sensitivity, specificity, and Dice coefficient. The system achieves robust performance even under varying illumination and noise conditions. These findings indicate that integrating adversarial learning with convolutional feature extraction can significantly enhance retinal vessel segmentation, paving the way for more efficient and automated retinal disease screening systems

Image restoration is a critical task in computer vision that involves recovering an original image from corrupted or damaged versions of it. Traditional image restoration relies on interpolation and completion techniques, such as Navier–Stokes equations and the fast multipole boundary element method. However, these methods often fail to capture the advanced semantic information of an image, leading to inaccurate restoration results. In recent years, generative adversarial networks (GANs) have emerged as a practical approach in computer vision for image restoration tasks, as they can address image restoration issues related to damaged or missing image information. GANs are a deep‐learning network structure with a generator and discriminator. In image restoration, the generator is employed to restore damaged images, and the discriminator is used to assess the authenticity of the repair results. Competition between the generator and discriminator improves the quality of the repair results. This study proposes a novel generative image restoration method that utilizes contextual and perceptual semantic information mechanisms to strengthen GANs. Our approach demonstrates the effectiveness of GANs in restoring images through learning how to fuse the missing or damaged parts of an image with the undamaged parts surrounding them, resulting in visually appealing restoration results.

In this study, we evaluated the improvement of image quality in digital breast tomosynthesis under low-radiation dose conditions of pre-reconstruction processing using conditional generative adversarial networks [cGAN (pix2pix)]. Pix2pix pre-reconstruction processing with filtered back projection (FBP) was compared with and without multiscale bilateral filtering (MSBF) during pre-reconstruction processing. Noise reduction and preserve contrast rates were compared using full width at half-maximum (FWHM), contrast-to-noise ratio (CNR), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) in the in-focus plane using a BR3D phantom at various radiation doses [reference-dose (automatic exposure control reference dose: AECrd), 50% and 75% reduction of AECrd] and phantom thicknesses (40 mm, 50 mm, and 60 mm). The overall performance of pix2pix pre-reconstruction processing was effective in terms of FWHM, PSNR, and SSIM. At ~50% radiation-dose reduction, FWHM yielded good results independently of the microcalcification size used in the BR3D phantom, and good noise reduction and preserved contrast. PSNR results showed that pix2pix pre-reconstruction processing represented the minimum in the error with reference FBP images at an approximately 50% reduction in radiation-dose. SSIM analysis indicated that pix2pix pre-reconstruction processing yielded superior similarity when compared with and without MSBF pre-reconstruction processing at ~50% radiation-dose reduction, with features most similar to the reference FBP images. Thus, pix2pix pre-reconstruction processing is promising for reducing noise with preserve contrast and radiation-dose reduction in clinical practice.

Pseudo CT Synthesis Using Cone-Beam CT of Cervical Cancer with GAN-Based Neural Network Model