Search

Unmanned aerial vehicles (UAVs) with cameras offer extensive monitoring capabilities and exceptional maneuverability, making them ideal for real-time ship detection and effective ship management. However, ship detection by camera-equipped UAVs faces challenges when it comes to multi-viewpoints, multi-scales, environmental variability, and dataset scarcity. To overcome these challenges, we proposed a data augmentation method based on stable diffusion to generate new images for expanding the dataset. Additionally, we improve the YOLOv8n OBB model by incorporating the BiFPN structure and EMA module, enhancing its ability to detect multi-viewpoint and multi-scale ship instances. Through multiple comparative experiments, we evaluated the effectiveness of our proposed data augmentation method and the improved model. The results indicated that our proposed data augmentation method is effective for low-volume datasets with complex object features. The YOLOv8n-BiFPN-EMA OBB model we proposed performed well in detecting multi-viewpoint and multi-scale ship instances, achieving the mAP (@0.5) of 92.3%, the mAP (@0.5:0.95) of 77.5%, a reduction of 0.8 million in model parameters, and a detection speed that satisfies real-time ship detection requirements. [ABSTRACT FROM AUTHOR]

• Image inpainting techniques enhance artefact digital reconstruction. • AI-based image inpainting reconstructs broken artefacts in 3D. • Versatile manipulation of 3D artefacts can be made for varied views. • The influence of input image quantity on 3D model fidelity is explored. • Visualizing point cloud differences showcases model quality changes. [Display omitted] Artificial intelligence can lend a helpful digital "hand" in the restoration process of deteriorated cultural heritage items as well as towards an increased visitor interest in the museum exhibits. To this purpose, the present paper proposes a deep learning approach to repair the missing content and to recreate a visual counterpart of a degraded artefact by a 3D rendering of the semantic inpainted version. The new approach is constructed by means of some of the most recent and successful deep learning models for image inpainting and 3D reconstruction, namely stable diffusion and neural radiance fields. The method is tested in the scenario of ceramic artefacts, where the end visual result has a bigger impact. The ability of the novel technique to creatively reproduce a realistic and plausible 3D surrogate of broken archaeological objects shows the potential that AI has in supporting specialists with preserving the cultural heritage and bringing the museums into the public spotlight. [ABSTRACT FROM AUTHOR]

This study proposes a novel self‐training framework for unsupervised domain adaptation in the segmentation of concrete wall cracks using accumulated crack data. The proposed method incorporates Bayesian neural networks for uncertainty estimation of pseudo‐labels, and spatial priors of cracks for screening noisy labels. Experiments demonstrate that the proposed approach achieves significant improvements in F1 score. Comparing the F1 scores, Bayesian DeepLabv3+ and Bayesian U‐Net showed performance improvements of 0.0588 and 0.1501, respectively, after domain adaptation. Furthermore, the integration of Stable Diffusion for few‐shot image generation enhances domain adaptation performance by 0.0332. The proposed framework enables high‐precision crack segmentation with as few as 100 target images, which can be easily obtained at the site, reducing the cost of model deployment in infrastructure maintenance. The study also investigates the optimal number of iterations for domain adaptation based on the uncertainty score, providing insights for practical implementation. The proposed method contributes to the development of efficient and automated structural health monitoring using AI. [ABSTRACT FROM AUTHOR]

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through additional visual guidance (e.g., sketches and semantic masks) but require additional training with annotated images. In this paper, we propose a method for spatially controlling text-to-image generation without further training of diffusion models. Our method is based on the insight that the cross-attention maps reflect the positional relationship between words and pixels. Our aim is to control the attention maps according to given semantic masks and text prompts. To this end, we first explore a simple approach of directly swapping the cross-attention maps with constant maps computed from the semantic regions. Some prior works also allow training-free spatial control of text-to-image diffusion models by directly manipulating cross-attention maps. However, these approaches still suffer from misalignment to given masks because manipulated attention maps are far from actual ones learned by diffusion models. To address this issue, we propose masked-attention guidance, which can generate images more faithful to semantic masks via indirect control of attention to each word and pixel by manipulating noise images fed to diffusion models. Masked-attention guidance can be easily integrated into pre-trained off-the-shelf diffusion models (e.g., Stable Diffusion) and applied to the tasks of text-guided image editing. Experiments show that our method enables more accurate spatial control than baselines qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

AbstractRecent advances in artificial intelligence-generated content (AIGC) have led to the rapid generation of high-quality images. AIGC has attracted the attention of commercial digital art asset creators. Traditional artist-led processes contrast with current AI tools that often reduce creators to passive roles. This study examines the integration of AI image generation into commercial digital art, emphasizing the importance of preserving creators’ creative autonomy. Our formative study (S1) involved interviews with commercial digital art creators, highlighting a need for greater control and transparency in AI-assisted painting. In response, we developed RealtimeGen, an integrated tool that merges human creativity with AI’s capabilities, allowing creators to intervene in the generative process. A user study (S2) comparing RealtimeGen with the popular AIGC tool Stable Diffusion was also carried out. The results showed its enhanced user experience and workflow compatibility. Our work contributes to understanding and improving AI-assisted painting workflows for commercial creators, offering them greater creative agency. [ABSTRACT FROM AUTHOR]

Due to the complexity and short timescale of detonation, it is usually difficult to capture its transient characteristics experimentally. Advanced numerical methods are essential for enhancing the understanding of the flow field structure and combustion mechanism of detonation. In this study, a density-based compressible reactive flow solver called CDSFoam is developed for simulating gas-droplet two-phase detonation combustion based on OpenFOAM. The primary feature of this solver is its implementation of two-way coupling between gas and liquid phases, utilizing the Eulerian–Lagrangian method. The key enhancement is an improved approximate Riemann solver used to solve the convective flux, reducing dissipation while ensuring robustness. Time integration is achieved through the third-order strong stability preserving Runge–Kutta method. Additionally, CDSFoam incorporates dynamic load balancing and adaptive mesh refinement techniques to mitigate computational costs while achieving high-resolution flow fields dynamically. To validate the reliability and accuracy of the solver, a series of benchmark cases are examined, including the multi-component inert and reactive shock tube, the stable diffusion process, the Riemann problem, the one-dimensional detonation, the two-dimensional detonation and oblique detonation, the droplet phase model, the two-dimensional gas–liquid two-phase detonation, and the two-phase rotating detonation. The results show that CDSFoam can well predict the shock wave discontinuity, shock wave induced ignition, molecular diffusion, detonation key parameters, detonation cell size, and the main characteristics of gas–liquid two-phase detonation. [ABSTRACT FROM AUTHOR]

An observation on the current state of teaching large language models (LLMs) in education is made. The problem of lacking a structural approach is defined. A methodology is created in order to serve as the basis of a workshop in teaching students with different types of backgrounds the correct use of LLMs and their capabilities. A workshop plan is created; instructions and materials are presented. A practical experiment has been conducted by dividing students into teams and guiding them to create a small project. Different LLMs are used for the purposes of creating a fictional story, images relating to the story, and very simple HTML, JS, and CSS code. Participants are given requirements that consider the limitations of LLMs, and different approaches to creatively solving arising issues due to the requirements are observed. The students' projects are hosted on the web, so that they can see the results of their work. They are given the opportunity to use them as motivation for their future development. A survey is created and distributed to all the participating students. The results are analyzed from different angles and conclusions are made on the effectiveness of the workshop in completing its goal of solving the defined problem. [ABSTRACT FROM AUTHOR]

Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges. [ABSTRACT FROM AUTHOR]

This research explores and discusses the visual symbolic imaginaries generated by four artificial intelligence (AI) programs regarding the Mexico-United States border. The visual production hinges upon six key concepts that emerge from the general theme: “Most relevant symbolic imaginaries of the wall, violence, woman, childhood, inequality, and migration related to the Mexico-United States border.” The AI programs used to produce the images are Midjourney, Leonardo.ai, Stable Diffusion, and Dall-E 2. An experimental methodology defines the key concepts and symbolic imaginaries at the border between the United States and Mexico through ChatGPT 3.5. The images have been obtained by translating the written concepts into images using such programs. The generative image programs are conceptualized based on the aesthetic apparatus theory and the posthuman vision. The images are analyzed using the theory of social, cultural, and symbolic imaginaries. The analysis reveals ideological biases and aesthetic tendencies in the visually synthesized symbolic imaginaries and rhetorical regimes of the Mexico-United States border through generative image production programs. It also builds a critical-sociopolitical perspective on three main aspects: a conceptualization of generative image programs as techno-aesthetic apparatuses, a reflection on the creative construction processes of visual discourses produced by AI devices, and an examination of the ideological and aesthetic biases of the images understood as techno-aesthetic objects obtained from this visual production technology. [ABSTRACT FROM AUTHOR]

In the sphere of urban renewal of historic districts, preserving and innovatively reinterpreting traditional architectural styles remains a primary research focus. However, the modernization and adaptive reuse of traditional buildings often necessitate changes in their functionality. To cater to the demands of tourism in historic districts, many traditional residential buildings require conversion to commercial use, resulting in a mismatch between their external form and their internal function. This study explored an automated approach to transform traditional residences into commercially viable designs, offering an efficient and scalable solution for the modernization of historic architecture. We developed a methodology based on diffusion models, focusing on a dataset of nighttime shopfront facades. By training a low-rank adaptation (LoRA) model and integrating the ControlNet model, we enhanced the accuracy and stability of the generated images. The methodology's performance was validated through qualitative and quantitative assessments, optimizing the batch size, repetition, and learning rate configurations. These evaluations confirmed the method's effectiveness. Our findings significantly advance the modern commercial style transformation of historical architectural facades, providing a novel solution that maintains the aesthetic and functional integrity, thereby fostering breakthroughs in traditional design thinking and exploring new possibilities for the preservation and commercial adaptation of historical buildings. [ABSTRACT FROM AUTHOR]

Conventional methods of teaching architectural design have flaws like fuzzy information exchange, limitations of thought dispersion, and disconnection of theory and practice because of the different cognitive levels of teachers and students. This paper explores the interactive and collaborative "human-machine-human" mode of utilizing Stable Diffusion image generation technology to teach architectural design and achieve artificial intelligence. To enhance the quality and effectiveness of instruction, the model uses artificial intelligence for image generation, optimization, and presentation in accordance with the three stages of architectural design teaching that are developed in this paper. Mainly using the Northeastern University youth hostel design course as an example, this paper compares the new "human-machine-human" mode with the traditional "human-human" mode, assesses the necessity and viability of the AI intervention, and offers examples for future architectural course teaching reform and the comprehensive integration of AI and architecture. In the interim, it offers resources and recommendations for the deep integration of AI and architecture, as well as recommendations for future teaching reform of architecture courses. [ABSTRACT FROM AUTHOR]

In recent years, the field of artificial intelligence has witnessed a remarkable surge in the generation of synthetic images, driven by advancements in deep learning techniques. These synthetic images, often created through complex algorithms, closely mimic real photographs, blurring the lines between reality and artificiality. This proliferation of synthetic visuals presents a pressing challenge: how to accurately and reliably distinguish between genuine and generated images. This article, in particular, explores the task of detecting images generated by text-to-image diffusion models, highlighting the challenges and peculiarities of this field. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable Diffusion and GLIDE. Our experiments show that it is possible to detect the generated images using simple multi-layer perceptrons (MLPs), starting from features extracted by CLIP or RoBERTa, or using traditional convolutional neural networks (CNNs). These latter models achieve remarkable performances in particular when pretrained on large datasets. We also observe that models trained on images generated by Stable Diffusion can occasionally detect images generated by GLIDE, but only on the MSCOCO dataset. However, the reverse is not true. Lastly, we find that incorporating the associated textual information with the images in some cases can lead to a better generalization capability, especially if textual features are closely related to visual ones. We also discovered that the type of subject depicted in the image can significantly impact performance. This work provides insights into the feasibility of detecting generated images and has implications for security and privacy concerns in real-world applications. The code to reproduce our results is available at: https://github.com/davide-coccomini/Detecting-Images-Generated-by-Diffusers. [ABSTRACT FROM AUTHOR]

In our research, we apply electrophoretic deposition (EPD) using AC voltage to investigate how high-C-rate electrochemical reactions affect pseudocapacitive charge storage in lithium iron phosphate (LFP) Li-ion batteries. This method significantly raises the battery's specific capacity, achieving ~90 mAh/g at a 1 C-rate, along with outstanding cycle stability. Although we observe some capacity reduction over numerous cycles, there is a notable increase in the pseudocapacitive contribution to the battery's charge storage. This is demonstrated by the consistent peak positions and currents during CV and a stable diffusion constant maintained at 9.6 × 10−9 cm2∙s−1. These findings highlight the battery's durability, especially in high-demand scenarios. After an extended cycling period of ~500 cycles, the redox peaks related to the Fe2+/Fe3+ redox processes remain unchanged in terms of magnitude and position, indicating the battery's excellent reversibility. [ABSTRACT FROM AUTHOR]

Accurately predicting homeowners' aesthetic preferences is crucial in interior design. This study develops a fine-tuning model (LORA) for interior design styles corresponding to different MBTI personality types, leveraging the Stable Diffusion Web UI platform and integrating it into a generative artificial intelligence framework. Subsequently, personalized aesthetic preference architectural interior renderings are recommended based on homeowners' personality traits, aiming to achieve an adaptive interior design approach. To achieve more precise adaptive solutions, this research surveys the style and color tendencies of respondents with different MBTI personality types and adds style description prompts to assist in image generation. The study finds that this method can better predict the interior design styles favored by certain MBTI personality types. This research contributes to addressing aesthetic biases between designers and homeowners, bringing innovative ideas and methods to interior design, and is expected to enhance homeowners' satisfaction. [ABSTRACT FROM AUTHOR]

Defect detection from images, an important application in the development of the industrial internet, has been gaining increasing attention due to its close relationship with product quality in industrial production. However, two major challenges in defect detection persist: (1) Limited availability of datasets. Deep learning-based models typically require large-scale training sets to achieve satisfactory detection results. (2) Insufficient image quality and low detection accuracy. When many object detection methods are applied to industrial defect detection, they often exhibit poor performance in handling unclear boundaries, complex backgrounds, noise, and textures. In this study, we propose an advanced defect detection method based on YOLO and Stable Diffusion (YOLO-SD). For the few-shot dataset, a controllable generation module is designed, that integrates CLIP, LoRA, and ControlNet based on Stable Diffusion. Among them, CLIP text inversion can generate the most suitable prompt words from the defect dataset, providing prompt input for Stable Diffusion. LoRA can intervene and adjust the image style of Stable Diffusion by training on the defect dataset in a fine-tuning way. ControlNet obtains boundary and depth maps through HED and Midas. For the insufficient image quality and low detection accuracy, an improved YOLO model with an attention-based Fusion Simulated Feature module (FSF) is built that extracts defect features of the original images and generated images, which provides richer semantic information to improve the detection accuracy. At the same time, in order to make the model lightweight, we introduce a test optimization strategy to improve the model training process. Extensive experiments on the NEU-DET steel defect dataset show that the images generated by our method can expand the dataset to train the model and achieve a certain improvement in defect detection. [ABSTRACT FROM AUTHOR]

Assays mimicking in vitro the concentration gradients triggering biological responses like those involved in fighting infections and blood clotting are essential for biomedical research. Microfluidic assays prove especially attractive as they allow precise control of gradient shape allied to a reduction in scale. Conventional microfluidic devices are fabricated using solid plastics that prevent direct access to responding cells. Fluid-walled microfluidics allows the manufacture of circuits on standard Petri dishes in seconds, coupled to simple operating methods; cell-culture medium sitting in a standard dish is confined to circuits by fluid walls made of an immiscible fluorocarbon. We develop and experimentally validate an analytical model of diffusion between two or more aqueous streams flowing at different rates into a fluid-walled conduit with the cross-section of a circular segment. Unlike solid walls, fluid walls morph during flows as pressures fall, with wall shape changing down the conduit. The model is validated experimentally for Fourier numbers < 0.1 using fluorescein diffusing between laminar streams. It enables a priori prediction of concentration gradients throughout a conduit, so allowing rapid circuit design as well as providing bio-scientists with an accurate way of predicting local concentrations of bioactive molecules around responsive and non-responsive cells. [ABSTRACT FROM AUTHOR]

In order to improve the efficiency and accuracy of multitarget detection of soldering defects on surface-mounted components in Printed Circuit Board (PCB) fabrication, we propose a sample generation method using Stable Diffusion Model and ControlNet, as well as a defect detection method based on the Swin Transformer. The method consists of two stages: First, high-definition original images collected in industrial production and the corresponding prompts are input to Stable Diffusion Model and ControlNet for automatic generation of nonindependent samples. Subsequently, we integrate Swin Transformer as the backbone into the Cascade Mask R-CNN to improve the quality of defect features extracted from the samples for accurate detection box localization and segmentation. Instead of segmenting individual components on the PCB, the method inspects all components in the field of view simultaneously over a larger area. The experimental results demonstrate the effectiveness of our method in scaling up nonindependent sample datasets, thereby enabling the generation of high-quality datasets. The method accurately recognizes targets and detects defect types when performing multitarget inspection on printed circuit boards. The analysis against other models shows that our improved defect detection and segmentation method improves the Average Recall (AR) by 2.8% and the mean Average Precision (mAP) by 1.9%. [ABSTRACT FROM AUTHOR]

Digital rock analysis is a promising approach for visualizing geological microstructures and understanding transport mechanisms for underground geo-energy resources exploitation. Accurate image reconstruction methods are vital for capturing the diverse features and variability in digital rock samples. Stable diffusion, a cutting-edge artificial intelligence model, has revolutionized computer vision by creating realistic images. However, its application in digital rock analysis is still emerging. This study explores the applications of stable diffusion in digital rock analysis, including enhancing image resolution, improving quality with denoising and deblurring, segmenting images, filling missing sections, extending images with outpainting, and reconstructing three-dimensional rocks from twodimensional images. The powerful image generation capability of diffusion models shed light on digital rock analysis, showing potential in filling missing parts of rock images, lithologic discrimination, and generating network parameters. In addition, limitations in existing stable diffusion models are also discussed, including the lack of real digital rock images, and not being able to fully understand the mechanisms behind physical processes. Therefore, it is suggested to develop new models tailored to digital rock images for further progress. In sum, the integration of stable diffusion into digital core analysis presents immense research opportunities and holds the potential to transform the field, ushering in groundbreaking advances. [ABSTRACT FROM AUTHOR]

The preservation of historical traditional architectural ensembles faces multifaceted challenges, and the need for facade renovation and updates has become increasingly prominent. In conventional architectural updating and renovation processes, assessing design schemes and the redesigning component are often time-consuming and labor-intensive. The knowledge-driven method utilizes a wide range of knowledge resources, such as historical documents, architectural drawings, and photographs, commonly used to guide and optimize the conservation, restoration, and management of architectural heritage. Recently, the emergence of artificial intelligence-generated content (AIGC) technologies has provided new solutions for creating architectural facades, introducing a new research paradigm to the renovation plans for historic districts with their variety of options and high efficiency. In this study, we propose a workflow combining Grasshopper with Stable Diffusion: starting with Grasshopper to generate concise line drawings, then using the ControlNet and low-rank adaptation (LoRA) models to produce images of traditional Minnan architectural facades, allowing designers to quickly preview and modify the facade designs during the renovation of traditional architectural clusters. Our research results demonstrate Stable Diffusion's precise understanding and execution ability concerning architectural facade elements, capable of generating regional traditional architectural facades that meet architects' requirements for style, size, and form based on existing images and prompt descriptions, revealing the immense potential for application in the renovation of traditional architectural groups and historic districts. It should be noted that the correlation between specific architectural images and proprietary term prompts still requires further addition due to the limitations of the database. Although the model generally performs well when trained on traditional Chinese ancient buildings, the accuracy and clarity of more complex decorative parts still need enhancement, necessitating further exploration of solutions for handling facade details in the future. [ABSTRACT FROM AUTHOR]

The timely detection of malnutrition in children is of paramount importance, as it allows for early intervention and treatment. This proactive approach not only prevents further health deterioration but also fosters proper growth, minimizing the long-term consequences of malnutrition, such as stunted growth, impaired cognitive development, and increased vulnerability to diseases. Our work encompasses the creation of a new dataset comprising images of children in Healthy, Undernourished, Stunting, and Wasting categories. The core objective is to assess the deep learning model performance in classifying these children images. The experimentation is carried out by varying epochs, batch size, optimizers AdamW, Adamax, and RMSprop; and different values of the learning rate 0.1, 0.01, 0.001, and 0.0001 during model training. The model is trained on image dataset constructed by cleaning images generated by the stable diffusion model. The model is tested on randomly selected child images from websites. The model successfully classified two classes with 95% accuracy, 97.6% F1 score, precision 97.6%, and 97.6% recall with Adam optimizers, 0.0001 learning rate, and Batch size 4. Additionally, for the four-class categorization scenario, the study broadens the classification. The model achieved 88.87% accuracy, 90.3% recall, 90.2% precision, and an F1 score of 90% for four-class categorization with AdamW optimization, 0.0001 learning rate, and batch size 6. These results are satisfactory for prediction of malnutrition category in children. [ABSTRACT FROM AUTHOR]

In the reassessment of early twenty-first-century art, 2022 emerges as pivotal, marking the advent of the creative artificial intelligence (AI) era. Innovations like ChatGPT and Stable Diffusion disrupted artistic norms, igniting debates on AI Art prohibition and fostering a non-fungible tokens (NFTs) market. Despite fears of the "extinction of the artist," historical precedents show artists adapting to new technologies, suggesting an evolution rather than a diminution of the artist's role, paralleled by an evolving definition of art. This study examines the impact of AI-generated art on traditional art creation, focusing on its integration in a digital art class dedicated to fine art production. It posits AI as a novel, iterative tool for creative problem-solving in the visual arts. The methodology involves a case study in a digital art class of ten students, who employed the Craiyon art generator for inspiration, akin to traditional sketchbooking, and refined their concepts in Adobe Photoshop. The results demonstrate AI's diverse applications in art education. Students varied in their use of AI, from almost complete AI-generated works to using AI-created layers as a basis for further development or inspiration for original concepts. This study highlights AI's multifaceted role in enhancing artistic creativity and informs its future integration in art education and practice. [ABSTRACT FROM AUTHOR]

A challenging goal of neural coding is to characterize the neural representations underlying visual perception. To this end, multi-unit activity (MUA) of macaque visual cortex was recorded in a passive fixation task upon presentation of faces and natural images. We analyzed the relationship between MUA and latent representations of state-of-the-art deep generative models, including the conventional and feature-disentangled representations of generative adversarial networks (GANs) (i.e., z- and w-latents of StyleGAN, respectively) and language-contrastive representations of latent diffusion networks (i.e., CLIP-latents of Stable Diffusion). A mass univariate neural encoding analysis of the latent representations showed that feature-disentangled w representations outperform both z and CLIP representations in explaining neural responses. Further, w-latent features were found to be positioned at the higher end of the complexity gradient which indicates that they capture visual information relevant to high-level neural activity. Subsequently, a multivariate neural decoding analysis of the feature-disentangled representations resulted in state-of-the-art spatiotemporal reconstructions of visual perception. Taken together, our results not only highlight the important role of feature-disentanglement in shaping high-level neural representations underlying visual perception but also serve as an important benchmark for the future of neural coding. Author summary: Neural coding seeks to understand how the brain represents the world by modeling the relationship between stimuli and internal neural representations thereof. This field focuses on predicting brain responses to stimuli (neural encoding) and deciphering information about stimuli from brain activity (neural decoding). Recent advances in generative adversarial networks (GANs; a type of machine learning model) have enabled the creation of photorealistic images. Like the brain, GANs also have internal representations of the images they create, referred to as "latents". More recently, a new type of feature-disentangled "w-latent" of GANs has been developed that more effectively separates different image features (e.g., color; shape; texture). In our study, we presented such GAN-generated pictures to a macaque with cortical implants and found that the underlying w-latents were accurate predictors of high-level brain activity. We then used these w-latents to reconstruct the perceived images with high fidelity. The remarkable similarities between our predictions and the actual targets indicate alignment in how w-latents and neural representations represent the same stimulus, even though GANs have never been optimized on neural data. This implies a general principle of shared encoding of visual phenomena, emphasizing the importance of feature disentanglement in deeper visual areas. [ABSTRACT FROM AUTHOR]

The generation of images from electroencephalography (EEG) signals has become a popular research topic in recent research because it can bridge the gap between brain signals and visual stimuli and has wide application prospects in neuroscience and computer vision. However, due to the high complexity of EEG signals, the reconstruction of visual stimuli through EEG signals continues to pose a challenge. In this work, we propose an EEG-ConDiffusion framework that involves three stages: feature extraction, fine-tuning of the pretrained model, and image generation. In the EEG-ConDiffusion framework, classification features of EEG signals are first obtained through the feature extraction block. Then, the classification features are taken as conditions to fine-tune the stable diffusion model in the image generation block to generate images with corresponding semantics. This framework combines EEG classification and image generation means to enhance the quality of generated images. Our proposed framework was tested on an EEG-based visual classification dataset. The performance of our framework is measured by classification accuracy, 50-way top-k accuracy, and inception score. The results indicate that the proposed EEG-Condiffusion framework can extract effective classification features and generate high-quality images from EEG signals to realize EEG-to-image conversion. [ABSTRACT FROM AUTHOR]

The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion‐based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state‐of‐the‐art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion‐based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike. [ABSTRACT FROM AUTHOR]

Generative artificial intelligence (AI) models have made significant progress in automating the creation of 3D shapes, which has the potential to transform car design. In engineering design and optimization, evaluating engineering metrics is crucial. To make generative models performance-aware and enable them to create high-performing designs, surrogate modeling of these metrics is necessary. However, the currently used representations of 3D shapes either require extensive computational resources to learn or suffer from significant information loss, which impairs their effectiveness in surrogate modeling. To address this issue, we propose a new 2D representation of 3D shapes. We develop a surrogate drag model based on this representation to verify its effectiveness in predicting 3D car drag. We construct a diverse dataset of 4535 high-quality 3D car meshes labeled by drag coefficients computed from computational fluid dynamics simulations to train our model. Our experiments demonstrate that our model can accurately and efficiently evaluate drag coefficients with an R2 value above 0.84 for various car categories. Our model is implemented using deep neural networks, making it compatible with recent AI image generation tools (such as stable diffusion) and a significant step toward the automatic generation of drag-optimized car designs. Moreover, we demonstrate a case study using the proposed surrogate model to guide a diffusion-based deep generative model for drag-optimized car body synthesis. [ABSTRACT FROM AUTHOR]

This article explores the use of generative AI (GenAI) in marketing content creation. It emphasizes the importance of high-quality content in marketing and explains how GenAI can revolutionize the content creation process. The article discusses the trade-offs between content quality and quantity and how GenAI can overcome these trade-offs. It provides examples of how GenAI can efficiently create more content and improve decision-making in marketing. The article also discusses the challenges and opportunities of using GenAI in marketing, including the need for personalized content distribution and unbiased training data. It concludes by highlighting the potential for GenAI to improve product design and search engine marketing. [Extracted from the article]

Since the AI 'architectural explosion' of 2022, and as things have become clearer but have not yet settled down, a whole raft of possibilities for creativity and commercial exploration are emerging. Architectural and urban designer Wanyu He explains some of these opportunities, and also reminds us of the ethical and societal concerns about this technology – its biases and blindnesses – which must be addressed before these new approaches can be applied equitably. [ABSTRACT FROM AUTHOR]

In the last thirty or so years, architects have embraced all manner of computer softwares and hardwares. This has often resulted in convoluted forms and a concentration on the part of architects to solve fabrication complexities at the expense of dexterous design explorations. Artist, designer and educator Andrew Kudless reminds us of the messy, illogical and contradictory aspects of design development, and that we have yet to develop something as multivalent in its evocative suggestions as the old‐fashioned 'hairy' sketch. [ABSTRACT FROM AUTHOR]