Diverse Images Research Articles

FEMSFNet: Feature Enhancement and Multi-Scales Fusion Network for SAR Aircraft Detection

Aircraft targets, as high-value subjects, are a focal point in Synthetic Aperture Radar (SAR) image interpretation. To tackle challenges like limited SAR aircraft datasets and shortcomings in existing detection algorithms (complexity, poor performance, weak generalization), we present the Feature Enhancement and Multi-Scales Fusion Network (FEMSFNet) for SAR aircraft detection. FEMSFNet employs diverse image augmentation and integrates optimized Squeeze-and-Excitation Networks (SE) with residual network (ResNet) in a SdE-Resblock structure for a lightweight yet accurate model. It introduces ssppf-CSP module, an improved pyramid pooling model, to prevent receptive field deviation in deep network training. Tailored for SAR aircraft detection, FEMSFNet optimizes loss functions, emphasizing both speed and accuracy. Evaluation on the SAR Aircraft Detection Dataset (SADD) demonstrates significant improvements compared to the contrasted algorithms: precision rate (92%), recall rate (96%), and F1 score (94%), with a maximum increase of 12.2% in precision, 12.9% in recall, and 13.3% in F1 score.

Comparative Analysis of Color Space and Channel, Detector, and Descriptor for Feature-Based Image Registration.

The current study aimed to quantify the value of color spaces and channels as a potential superior replacement for standard grayscale images, as well as the relative performance of open-source detectors and descriptors for general feature-based image registration purposes, based on a large benchmark dataset. The public dataset UDIS-D, with 1106 diverse image pairs, was selected. In total, 21 color spaces or channels including RGB, XYZ, Y'CrCb, HLS, L*a*b* and their corresponding channels in addition to grayscale, nine feature detectors including AKAZE, BRISK, CSE, FAST, HL, KAZE, ORB, SIFT, and TBMR, and 11 feature descriptors including AKAZE, BB, BRIEF, BRISK, DAISY, FREAK, KAZE, LATCH, ORB, SIFT, and VGG were evaluated according to reprojection error (RE), root mean square error (RMSE), structural similarity index measure (SSIM), registration failure rate, and feature number, based on 1,950,984 image registrations. No meaningful benefits from color space or channel were observed, although XYZ, RGB color space and L* color channel were able to outperform grayscale by a very minor margin. Per the dataset, the best-performing color space or channel, detector, and descriptor were XYZ/RGB, SIFT/FAST, and AKAZE. The most robust color space or channel, detector, and descriptor were L*a*b*, TBMR, and VGG. The color channel, detector, and descriptor with the most initial detector features and final homography features were Z/L*, FAST, and KAZE. In terms of the best overall unfailing combinations, XYZ/RGB+SIFT/FAST+VGG/SIFT seemed to provide the highest image registration quality, while Z+FAST+VGG provided the most image features.

Optimizing OCR Performance: An Investigation into Image Preprocessing Techniques

This study investigates the impact of various image processing techniques on the accuracy of text extraction by PaddleOCR. The research explores how inversion, noise reduction, erosion, dilation, and grayscaling can pre-process images to improve the performance of PaddleOCR. Initially, the OCR’s effectiveness is assessed using unprocessed images. Subsequently, each image processing method is applied individually to evaluate its contribution to the accuracy of text detection. The findings aim to identify the most beneficial preprocessing technique for enhancing the accuracy of PaddleOCR in text extraction tasks. This research has implications for the optimization of OCR technology in digitizing textual content from diverse image backgrounds. Key Words: OCR optimization, image preprocessing, paddleOCR, image to text

Multi-modal medical image fusion using improved dual-channel PCNN.

This paper proposes a medical image fusion method in the non-subsampled shearlet transform (NSST) domain to combine a gray-scale image with the respective pseudo-color image obtained through different imaging modalities. The proposed method applies a novel improved dual-channel pulse-coupled neural network (IDPCNN) model to fuse the high-pass sub-images, whereas the Prewitt operator is combined with maximum regional energy (MRE) to construct the fused low-pass sub-image. First, the gray-scale image and luminance of the pseudo-color image are decomposed using NSST to find the respective sub-images. Second, the low-pass sub-images are fused by the Prewitt operator and MRE-based rule. Third, the proposed IDPCNN is utilized to get the fused high-pass sub-images from the respective high-pass sub-images. Fourth, the luminance of the fused image is obtained by applying inverse NSST on the fused sub-images, which is combined with the chrominance components of the pseudo-color image to construct the fused image. A total of 28 diverse medical image pairs, 11 existing methods, and nine objective metrics are used in the experiment. Qualitative and quantitative fusion results show that the proposed method is competitive with and even outpaces some of the existing medical fusion approaches. It is also shown that the proposed method efficiently combines two gray-scale images.

Medical image encryption system based on a simultaneous permutation and diffusion framework utilizing a new chaotic map

In telemedicine, diverse medical images transmitted between doctors and patients contain sensitive personal information. Thus, there is an urgent need for reliable and efficient medical image encryption to protect these medical images during transmission. In this paper, a simultaneous permutation and diffusion framework (SPDF) is introduced for medical image encryption based on a new chaotic map. Firstly, combining the Chebyshev map and the iterative chaotic map with infinite collapse (ICMIC), we propose a one-dimensional chaotic system (1D-CICMIC) which exhibits higher ergodicity and unpredictability compared to other 1D chaotic maps through comprehensive analyses. Secondly, in order to enhance permutation effect, we modify traditional Josephus traversing with a dynamic scrambling method where the scrambling scheme of the current pixel depends on the value of the previous diffused pixel. Thirdly, we develop a simultaneous permutation and diffusion framework, wherein the diffusion is embedded into the modified Josephus traversing to prevent attackers from targeting the scrambling and diffusion phases separately. Finally, based on 1D-CICMIC and SPDF, an encryption system is proposed. It adopts plaintext correlation in the diffusion operation, which strikes a balance between ciphertext sensitivity and plaintext sensitivity, offering resistance against chosen-plaintext attack (CPA), noise attack and data loss. Simulation results show that the proposed algorithm has high encryption efficiency and can withstand various common attacks.

Earlier laryngeal cancer detection using hybrid M-RCNN technique

One of the most common types of cancer is Laryngeal cancer, which has a high mortality rate. The primary malignant tumor responsible for this disease is squamous cell carcinoma (SCC). Early diagnosis is very important to avoid experiencing morbidity and mortality. Various tools and techniques are used to detect and monitor laryngeal cancers. Unfortunately, these tools and techniques have various limitations, for example, Existing tools and approaches Mask R-CNN for identifying laryngeal cancer have various performance limitations. These include the inability to accurately identify the disease in its early stages, the complexity of the computational environment, and the time-consuming process of conducting patient screenings by utilizing diverse image datasets, but it lagging to detect large dataset. In this paper, we present a hybrid deep-learning model which can be used to analyze and monitor the different symptoms of laryngeal cancers. Proposed model takes Laryngeal cancer dataset as input; preprocessing is done using median filter, then data augmentation is applied to increase data diversity, then feature extraction is performed using LBP-KNN, finally cancer identification/classification is done using Mask-RCNN. Proposed model attains Accuracy:99.3%; Precision:97.99%; Recall:98.09% and F-measure: 97.01%. This method could be useful in providing clinical support to radiologists and doctors. The proposed model can be used to detect minor malignancies in patients in a fast and accurate manner. It can also help improve the efficiency of the clinical process by allowing clinicians to screen more patients.

Multi-task learning with self-learning weight for image denoising

BackgroundImage denoising technology removes noise from the corrupted image by utilizing different features between image and noise. Convolutional neural network (CNN)-based algorithms have been the concern of the recent progress on diverse image restoration problems and become an efficient solution in image denoising.ObjectiveAlthough a quite number of existing CNN-based image denoising methods perform well on the simplified additive white Gaussian noise (AWGN) model, their performance often degrades severely on the real-world noisy images which are corrupted by more complicated noise.MethodsIn this paper, we utilized the multi-task learning (MTL) framework to integrate multiple loss functions for collaborative training of CNN. This approach aims to improve the denoising performance of CNNs on real-world images with non-Gaussian noise. Simultaneously, to automatically optimize the weights of individual sub-tasks within the MTL framework, we incorporated a self-learning weight layer into the CNN.ResultsExtensive experiments demonstrate that our approach effectively enhances the denoising performance of CNN-based image denoising algorithms on real-world images. It reduces excessive image smoothing, improves quantitative metrics, and enhances visual quality in the restored images.ConclusionOur method shows the effectiveness of the improved performance of denoising CNNS for real-world image denoising processing.

Generative data augmentation by conditional inpainting for multi-class object detection in infrared images

Multi-class object detection in infrared images is important in military and civilian use. Deep learning methods can obtain high accuracy but require a large-scale dataset. We propose a generative data augmentation framework DOCI-GAN, for infrared multi-class object detection with limited data. Contributions of this paper are four-folds. Firstly, DOCI-GAN is designed as a conditional image inpainting framework, yielding paired infrared multi-class object image and annotation. Secondly, a text-to-image converter is formulated to transform text-format object annotations to bounding box mask images, leading the augmentation to be mask-image-to-raw-image translation. Thirdly, a multiscale morphological erosion-based loss is created to alleviate the intensity inconsistency between inpainted local backgrounds and global background. Finally, for generating diverse images, artificial multi-class object annotations are integrated with real ones during augmentation. Experimental results demonstrated that DOCI-GAN augments dataset with high-quality infrared multi-class object images, consequently improving the accuracy of object detection baselines.

Synergizing Diffusion Models and Psychological Insights in Game Character Design

This study investigates the integration of diffusion models and psychological principles in game character design, a pivotal factor in augmenting player engagement in the dynamic gaming industry. Recognized for their proficiency in generating diverse and superior quality images, diffusion models are employed to systematize and refine the character design process. This methodological approach not only boosts efficiency but also fosters creativity in formulating character concepts. The research highlights the critical role of integrating psychological insights, aiming to align character designs more intimately with the emotional and psychological needs of players. By melding the technical prowess of diffusion models with a deep understanding of psychology, this study introduces a structured and efficient methodology for creating game characters. This novel approach ensures characters are not only visually striking but also emotionally engaging, deepening the bond between player and character and potentially enhancing player immersion. The study emphasizes the untapped potential of diffusion models in artistic endeavors and the significance of psychological considerations in game design, laying the groundwork for future innovations in this arena.

SkyGPT: Probabilistic ultra-short-term solar forecasting using synthetic sky images from physics-constrained VideoGPT

The variability of solar photovoltaic (PV) power output, driven by rapidly changing cloud dynamics, hinders the transition to reliable renewable energy systems. Information on future sky conditions, especially cloud coverage, holds the promise for improving PV output forecasting. Leveraging recent advances in generative artificial intelligence (AI), we introduce SkyGPT, a physics-constrained stochastic video prediction model, which predicts plausible future images of the sky using historical sky images. We show that SkyGPT can accurately capture cloud dynamics, producing highly realistic and diverse future sky images. We further demonstrate its efficacy in 15-minute-ahead probabilistic PV output forecasting using real-world power generation data from a 30-kW rooftop PV system. By coupling SkyGPT with a U-Net-based PV power prediction model, we observe superior prediction reliability and sharpness compared with several benchmark methods. The propose approach achieves a continuous ranked probability score (CRPS) of 2.81 kW, outperforming a classic convolutional neural network (CNN) baseline by 13% and the smart persistence model by 23%. The findings of this research could aid efficient and resilient management of solar electricity generation, particularly as we transition to renewable-heavy grids. The study also provides valuable insights into stochastic cloud modeling for a broad research community, encompassing fields such as solar energy meteorology and atmospheric sciences.

Artificial Intelligence in Medical Imaging: Analyzing the Performance of ChatGPT and Microsoft Bing in Scoliosis Detection and Cobb Angle Assessment.

Open-source artificial intelligence models (OSAIM) find free applications in various industries, including information technology and medicine. Their clinical potential, especially in supporting diagnosis and therapy, is the subject of increasingly intensive research. Due to the growing interest in artificial intelligence (AI) for diagnostic purposes, we conducted a study evaluating the capabilities of AI models, including ChatGPT and Microsoft Bing, in the diagnosis of single-curve scoliosis based on posturographic radiological images. Two independent neurosurgeons assessed the degree of spinal deformation, selecting 23 cases of severe single-curve scoliosis. Each posturographic image was separately implemented onto each of the mentioned platforms using a set of formulated questions, starting from 'What do you see in the image?' and ending with a request to determine the Cobb angle. In the responses, we focused on how these AI models identify and interpret spinal deformations and how accurately they recognize the direction and type of scoliosis as well as vertebral rotation. The Intraclass Correlation Coefficient (ICC) with a 'two-way' model was used to assess the consistency of Cobb angle measurements, and its confidence intervals were determined using the F test. Differences in Cobb angle measurements between human assessments and the AI ChatGPT model were analyzed using metrics such as RMSEA, MSE, MPE, MAE, RMSLE, and MAPE, allowing for a comprehensive assessment of AI model performance from various statistical perspectives. The ChatGPT model achieved 100% effectiveness in detecting scoliosis in X-ray images, while the Bing model did not detect any scoliosis. However, ChatGPT had limited effectiveness (43.5%) in assessing Cobb angles, showing significant inaccuracy and discrepancy compared to human assessments. This model also had limited accuracy in determining the direction of spinal curvature, classifying the type of scoliosis, and detecting vertebral rotation. Overall, although ChatGPT demonstrated potential in detecting scoliosis, its abilities in assessing Cobb angles and other parameters were limited and inconsistent with expert assessments. These results underscore the need for comprehensive improvement of AI algorithms, including broader training with diverse X-ray images and advanced image processing techniques, before they can be considered as auxiliary in diagnosing scoliosis by specialists.

The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods

PurposeThis study aimed to examine the robustness of positron emission tomography (PET) radiomic features extracted via different segmentation methods before and after ComBat harmonization in patients with non-small cell lung cancer (NSCLC).MethodsWe included 120 patients (positive recurrence = 46 and negative recurrence = 74) referred for PET scanning as a routine part of their care. All patients had a biopsy-proven NSCLC. Nine segmentation methods were applied to each image, including manual delineation, K-means (KM), watershed, fuzzy-C-mean, region-growing, local active contour (LAC), and iterative thresholding (IT) with 40, 45, and 50% thresholds. Diverse image discretizations, both without a filter and with different wavelet decompositions, were applied to PET images. Overall, 6741 radiomic features were extracted from each image (749 radiomic features from each segmented area). Non-parametric empirical Bayes (NPEB) ComBat harmonization was used to harmonize the features. Linear Support Vector Classifier (LinearSVC) with L1 regularization For feature selection and Support Vector Machine classifier (SVM) with fivefold nested cross-validation was performed using StratifiedKFold with ‘n_splits’ set to 5 to predict recurrence in NSCLC patients and assess the impact of ComBat harmonization on the outcome.ResultsFrom 749 extracted radiomic features, 206 (27%) and 389 (51%) features showed excellent reliability (ICC ≥ 0.90) against segmentation method variation before and after NPEB ComBat harmonization, respectively. Among all, 39 features demonstrated poor reliability, which declined to 10 after ComBat harmonization. The 64 fixed bin widths (without any filter) and wavelets (LLL)-based radiomic features set achieved the best performance in terms of robustness against diverse segmentation techniques before and after ComBat harmonization. The first-order and GLRLM and also first-order and NGTDM feature families showed the largest number of robust features before and after ComBat harmonization, respectively. In terms of predicting recurrence in NSCLC, our findings indicate that using ComBat harmonization can significantly enhance machine learning outcomes, particularly improving the accuracy of watershed segmentation, which initially had fewer reliable features than manual contouring. Following the application of ComBat harmonization, the majority of cases saw substantial increase in sensitivity and specificity.ConclusionRadiomic features are vulnerable to different segmentation methods. ComBat harmonization might be considered a solution to overcome the poor reliability of radiomic features.

Developing a Pain Identification Model Using a Deep Learning Technique

In this study, the authors proposed a pain identification model using facial expressions. An image extraction technique was developed using the liquid neural network to extract diverse images from the video files. The authors used the DenseNet 201 and MobileNet V3 models to build a hybrid feature engineering technique. They applied quantization aware training to improve the efficiency of the models. The Prkachin and Solomon Pain Intensity score was used for the image classification. They fine-tuned the LightGBM model using the random search algorithm for identifying pain from the facial images. The authors used the Denver Intensity of Spontaneous Facial Action dataset to generalize the proposed model. The performance evaluation outlined the significant performance of the proposed model in identifying pain using the images. In addition, it demands limited computational resources to identify pain. Healthcare and rehabilitation centers can implement the proposed model to provide adequate services to disabled individuals.

Advancements In Multi-Modality Medical Image Fusion: A Comprehensive Review

Multimodality medical image fusion involves the amalgamation of multiple images acquired through single or multiple imaging modalities. The purpose of medical image fusion methods is to enhance the quality of medical images by effectively capturing the key features within the fused output. This consequently enhances the practicality of medical images for diagnostic assessment and issue identification. Medical imaging modalities like magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) have been developed and are extensively utilized for clinical diagnoses. These multimodality images harbor vital information crucial for precise and efficient diagnosis of brain ailments. As a result, amalgamating diverse image modalities in the medical domain to create a distinct image brimming with intricate anatomical details and heightened spectral information has become exceedingly valuable in clinical diagnosis. This manuscript offers an exhaustive examination of existing literature on image fusion, elucidating the fundamental concepts and materials essential for a comprehensive grasp of diverse medical fusion techniques.

The Use and Application of Mangas as Course Materials in Intermediate Japanese Language Teaching for Turks: An Active Learning Method in Online Classrooms

The purpose of this study is to clarify the potential of using manga as a teaching tool in Japanese language education in Turkey. Manga is generally recognized as an entertainment product, with a wide variety of genres and diverse images of manga. In addition, prejudice against manga also exists. Therefore, it is necessary to first analyze learners’ candid feedback on the academic use of manga and present an evaluation of its usefulness as a teaching material. This will diversify Japanese language education, which has been limited to conventional teaching materials, and will motivate learners to learn more, thereby contributing to the discovery of effective teaching methods, the improvement of Japanese language teaching methods, and the development of educational programs. This research can be positioned as basic research to provide more attractive and effective Japanese language education.

Lusca: FIJI (ImageJ) based tool for automated morphological analysis of cellular and subcellular structures

The human body consists of diverse subcellular, cellular and supracellular structures. Neurons possess varying-sized projections that interact with different cellular structures leading to the development of highly complex morphologies. Aiming to enhance image analysis of complex biological forms including neurons using available FIJI (ImageJ) plugins, Lusca, an advanced open-source tool, was developed. Lusca utilizes machine learning for image segmentation with intensity and size thresholds. It performs particle analysis to ascertain parameters such as area/volume, quantity, and intensity, in addition to skeletonization for determining length, branching, and width. Moreover, in conjunction with colocalization measurements, it provides an extensive set of 29 morphometric parameters for both 2D and 3D analysis. This is a significant enhancement compared to other scripts that offer only 5–15 parameters. Consequently, it ensures quicker and more precise quantification by effectively eliminating noise and discerning subtle details. With three times larger execution speed, fewer false positive and negative results, and the capacity to measure various parameters, Lusca surpasses other existing open-source solutions. Its implementation of machine learning-based segmentation facilitates versatile applications for different cell types and biological structures, including mitochondria, fibres, and vessels. Lusca’s automated and precise measurement capability makes it an ideal choice for diverse biological image analyses.

Data augmentation-based enhanced fingerprint recognition using deep convolutional generative adversarial network and diffusion models

The progress of fingerprint recognition applications encounters substantial hurdles due to privacy and security concerns, leading to limited fingerprint data availability and stringent data quality requirements. This article endeavors to tackle the challenges of data scarcity and data quality in fingerprint recognition by implementing data augmentation techniques. Specifically, this research employed two state-of-the-art generative models in the domain of deep learning, namely Deep Convolutional Generative Adversarial Network (DCGAN) and the Diffusion model, for fingerprint data augmentation. Generative Adversarial Network (GAN), as a popular generative model, effectively captures the features of sample images and learns the diversity of the sample images, thereby generating realistic and diverse images. DCGAN, as a variant model of traditional GAN, inherits the advantages of GAN while alleviating issues such as blurry images and mode collapse, resulting in improved performance. On the other hand, Diffusion, as one of the most popular generative models in recent years, exhibits outstanding image generation capabilities and surpasses traditional GAN in some image generation tasks. The experimental results demonstrate that both DCGAN and Diffusion can generate clear, high-quality fingerprint images, fulfilling the requirements of fingerprint data augmentation. Furthermore, through the comparison between DCGAN and Diffusion, it is concluded that the quality of fingerprint images generated by DCGAN is superior to the results of Diffusion, and DCGAN exhibits higher efficiency in both training and generating images compared to Diffusion.

SADSNet: A robust 3D synchronous segmentation network for liver and liver tumors based on spatial attention mechanism and deep supervision.

• Introduce a data augmentation strategy to expand the required different morphological data during the training and learning phase, and improve the algorithm's feature learning ability for complex and diverse tumor morphology CT images.• Design attention mechanisms for encoding and decoding paths to extract fine pixel level features, improve feature extraction capabilities, and achieve efficient spatial channel feature fusion.• The deep supervision layer is used to correct and decode the final image data to provide high accuracy of results.• The effectiveness of this method has been affirmed through validation on the LITS, 3DIRCADb, and SLIVER datasets. Accurately extracting liver and liver tumors from medical images is an important step in lesion localization and diagnosis, surgical planning, and postoperative monitoring. However, the limited number of radiation therapists and a great number of images make this work time-consuming. This study designs a spatial attention deep supervised network (SADSNet) for simultaneous automatic segmentation of liver and tumors. Firstly, self-designed spatial attention modules are introduced at each layer of the encoder and decoder to extract image features at different scales and resolutions, helping the model better capture liver tumors and fine structures. The designed spatial attention module is implemented through two gate signals related to liver and tumors, as well as changing the size of convolutional kernels; Secondly, deep supervision is added behind the three layers of the decoder to assist the backbone network in feature learning and improve gradient propagation, enhancing robustness. The method was testing on LITS, 3DIRCADb, and SLIVER datasets. For the liver, it obtained dice similarity coefficients of 97.03%, 96.11%, and 97.40%, surface dice of 81.98%, 82.53%, and 86.29%, 95% hausdorff distances of 8.96 mm, 8.26 mm, and 3.79 mm, and average surface distances of 1.54 mm, 1.19 mm, and 0.81 mm. Additionally, it also achieved precise tumor segmentation, which with dice scores of 87.81% and 87.50%, surface dice of 89.63% and 84.26%, 95% hausdorff distance of 12.96 mm and 16.55 mm, and average surface distances of 1.11 mm and 3.04 mm on LITS and 3DIRCADb, respectively. The experimental results show that the proposed method is effective and superior to some other methods. Therefore, this method can provide technical support for liver and liver tumor segmentation in clinical practice.

The multimodality cell segmentation challenge: toward universal solutions.

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimental settings. Here, we present a multimodality cell segmentation benchmark, comprising more than 1,500 labeled images derived from more than 50 diverse biological experiments. The top participants developed a Transformer-based deep-learning algorithm that not only exceeds existing methods but can also be applied to diverse microscopy images across imaging platforms and tissue types without manual parameter adjustments. This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging.

A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a discrepancy between novice-user-input prompts and the model-preferred prompts. To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization. For CFP, we construct a novel dataset for text-to-image tasks that combines coarse and fine-grained prompts to facilitate the development of automated prompt generation methods. For UF-FGTG, we propose a novel framework that automatically translates user-input prompts into model-preferred prompts. Specifically, we propose a prompt refiner that continually rewrites prompts to empower users to select results that align with their unique needs. Meanwhile, we integrate image-related loss functions from the text-to-image model into the training process of text generation to generate model-preferred prompts. Additionally, we propose an adaptive feature extraction module to ensure diversity in the generated results. Experiments demonstrate that our approach is capable of generating more visually appealing and diverse images than previous state-of-the-art methods, achieving an average improvement of 5% across six quality and aesthetic metrics. Data and code are available at https://github.com/Naylenv/UF-FGTG.