Computer-generated Images Research Articles

Anatomical assessment of cerebral sulci and gyri for neuroanatomy education using photogrammetry technique to generate 3D-tridimensional models.

The surface of the brain is characterized by sulci and gyri. From these surface features, we can identify the frontal, parietal, temporal, occipital, and insular lobes. Learning neuroanatomy traditionally involves studying anatomical figures from atlases and working with cadaveric specimens in the lab. In higher education, technology, such as computer-generated images and three-dimensional (3D) models, can enhance students' understanding and retention of the material. The photogrammetry technique, which involves capturing images with digital cameras or smartphones, allows for the creation of low-cost 3D anatomical models. Five human cadaver brains were microsurgically dissected to expose the sulci and gyri. Using smartphones and free software, tridimensional brain models were created using the photogrammetry technique, with a detailed step-by-step description. The digital models were stored for use in teaching neuroanatomy. Human brains were dissected by removing the arachnoid membrane under microscopic visualization. Using smartphones and free software, tridimensional brain models were created with appropriate visualization in details of the sulci and gyri. These models were stored on computers and made available to neuroanatomy students via the Internet. By using smartphones and low-cost software applications, the pedagogy of neuroanatomy in higher education can be enhanced, providing students with online access to spatially accurate brain models. This improves their ability to perceive the spatial structure of brain specimens.

Liquid crystal-based image holography with broadband response and polarization insensitivity.

We propose and experimentally demonstrate liquid crystal-based computer-generated image holography enabled by the Pancharatnam-Berry phase modulation. Such a device exhibits distinctive properties, such as natural light illumination, polarization insensitivity, broadband optical response, high polarization conversion efficiency, and direct visibility to the naked eye. These unique attributes make this type of image holography a promising avenue for applications in optical information storage, anti-counterfeiting, and advanced information displays.

Improving the Generalization and Robustness of Computer‐Generated Image Detection Based on Contrastive Learning

With the rapid development of image generation techniques, it becomes much more difficult to distinguish high‐quality computer‐generated (CG) images from photographic (PG) images, challenging the authenticity and credibility of digital images. Therefore, distinguishing CG images from PG images has become an important research problem in image forensics, and it is crucial to develop reliable methods to detect CG images in practical scenarios. In this paper, we proposed a forensics contrastive learning (FCL) framework to adaptively learn intrinsic forensics features for the general and robust detection of CG images. The data augmentation module is specially designed for CG image forensics, which reduces the interference of forensic‐irrelevant information and enhances discrimination features between CG and PG images in both the spatial and frequency domains. Instance‐wise contrastive loss and patch‐wise contrastive loss are simultaneously applied to capture critical discrepancies between CG and PG images from global and local views. Extensive experiments on different public datasets and common postprocessing operations demonstrate that our approach can achieve significantly better generalization and robustness than the state‐of‐the‐art approaches. This manuscript was submitted as a pre‐print in the following link https://papers.ssrn.com/-sol3/papers.cfm?abstract_id=4778441.

The Effect of Simulating Virtual Scenes using Artificial Intelligence Techniques in Producing Various Media Materials

Our current era is witnessing continuous change and rapid development in various aspects of life, including technical development and scientific progress. Modern technologies like simulation and artificial intelligence (AI) significantly enhance media content creation and distribution in various ways: Content Creation: AI tools can generate scripts, edit videos, create animations, and produce music, allowing creators to streamline the production process and reduce costs. Personalization: AI algorithms analyze user preferences and behavior to deliver personalized content recommendations, improving user engagement and satisfaction. Simulations: Simulation technologies can create realistic virtual environments for training, gaming, and storytelling, providing immersive experiences for users. Quality Enhancement: AI can automatically enhance audio and video quality, detect errors or inconsistencies, and improve overall production value. Data Analysis: AI helps analyze audience data to inform content strategies, predict trends, and optimize marketing efforts. Simulation and AI are transforming media content by making it more efficient, engaging, and tailored to audiences. The study aims to identify the impact of using these modern technologies in the field of media, which includes the latest technological developments, by utilizing virtual viewer simulations through artificial intelligence techniques, and achieving the highest levels of awareness for producing various media materials. The research also addresses the key stages that a designer goes through and how we can benefit from the study to develop these stages in order to enhance the role of visual communication and interaction between the recipient and the sender through the use of digital media designed within the media content via artificial intelligence to convey the advertising message, and its role in influencing consumer motivations to attract and guide them in making decisions through artificial intelligence techniques that provide a clear vision of the design environment. The research highlights the importance of graphic design as an essential element in improving viewers’ experience of modern digital media and achieving a more realistic simulation, pointing to the development of the concept of simulation used in modern digital media and Computer-Generated Image (CGI) techniques. This research also aims to explore the vital role that graphic design plays at every stage of the production of digital technologies to achieve a more realistic simulation of virtual scenes in digital media. Hence, the research problem the extent to which media content, in terms of form and substance, benefits from these modern technologies (simulation - Artificial intelligence) and the impact of these technologies in making media content more credible through their use. The research hypotheses: Has the media content become more attractive with the use of these technologies (simulation Artificial intelligence)? Has the media content become more shareable across different platforms in form and substance with the use of these technologies (simulation - Artificial intelligence)? Has the media content become more appealing with the use of these technologies (simulation - Artificial intelligence)? Has the media content become more effective in the visual communication process with the use of these technologies (simulation - Artificial intelligence)? Has the use of these technologies (simulation - Artificial intelligence) provided competitive advantages for various media outlets? Has the use of these technologies (simulation - Artificial intelligence) offered marketing and promotional advantages for various media outlets? What are the positives and negatives of these technologies (simulation - Artificial intelligence) in the media? The main aim of the research the extent to which media content, in terms of form and substance, benefits from modern technologies (simulation – Artificial intelligence) and the impact of these technologies on enriching, supporting, and developing media content to make it more competitive and credible through their use. The importance of research in studying the role and impact of modern technologies, such as virtual scene simulation, using artificial intelligence techniques to produce various types of media content. It emphasizes the role of these technologies in influencing different media outlets regarding competitive advantages, marketing, and promotion, as well as highlighting the positives and negatives of these technologies. The research methodology is based on the analytical description approach.

The Influence Mechanism of Narrative Strategies Used by Virtual Influencers on Consumer Product Preferences

As social media has risen, virtual social media influencers have become a significant tool in modern marketing, utilizing computer-generated images (CGI), machine learning algorithms, and artificial intelligence technologies to connect with consumers via virtual online personas. In this study, the Uses and Gratifications Theory (UGT) is employed as a theoretical framework to explore the effects of educational narrative strategies and evaluative narrative strategies on consumer product preferences, with an analysis of the mediating role of word-of-mouth effectiveness and the moderating role of perceived product usability. It was demonstrated in Experiment 1 that virtual influencers employing educational narrative strategies are more effective than those using evaluative narrative strategies in enhancing consumer product preferences. The boundaries of the study were clarified in Experiment 2, which found that the main effect of educational narrative strategies utilized by social media influencers to increase consumer product preferences is present only in the context of virtual influencers. In Experiment 3, the mediating role of word-of-mouth recommendation effectiveness in the relationship between narrative strategies and consumer product preferences was further verified. The moderating role of perceived product usability was examined in Experiment 4, and it was found that the main effect is more pronounced in contexts where perceived product usability is low. The results of this study provide theoretical and practical guidance on how companies can effectively leverage virtual influencers to promote their products.

Characterization of human lightness discrimination thresholds for independent spectral variations.

The lightness of an object is an intrinsic property that depends on its surface reflectance spectrum. The visual system estimates an object's lightness from the light reflected off its surface. However, the reflected light also depends on object extrinsic properties of the scene, such as the light source. For stable perception, the visual system needs to discount the variations due to the object extrinsic properties. We characterize this perceptual stability for variation in two spectral properties of the scene: the reflectance spectra of background objects and the intensity of light sources. We measure human observers' thresholds of discriminating computer-generated images of 3D scenes based on the lightness of a spherical target object in the scene. We measured change in discrimination thresholds as we varied the reflectance spectra of the objects and the intensity of the light sources in the scene, both individually and simultaneously. For small amounts of extrinsic variations, the discrimination thresholds remained nearly constant indicating that the thresholds were dominated by observers' intrinsic representation of lightness. As extrinsic variation increased, it started affecting observers' lightness judgment and the thresholds increased. We estimated that the effects of extrinsic variations were comparable to observers' intrinsic variation in the representation of object lightness. Moreover, for simultaneous variation of these spectral properties, the increase in threshold squared compared to the no-variation condition was a linear sum of the corresponding increase in threshold squared for the individual properties, indicating that the variations from these independent sources combine linearly.

The Immersive Experience of the Era of Nuclear Energy in Emilija Škarnulytė’s Ecodocumentary Burial (2022)

The article examines Emilija Škarnulytė’s essay documentary Burial (Kapi­nynas, 2022) and its unique approach to engaging the audience with the themes of nature, atomic energy, and the nuclear era. It discusses how immersive techniques of aural and visual narrative, consisting of visual and acoustic material from diverse sources, such as images of former uranium mines in Kowary, the decommissioned Ignalina Nuclear Power Plant, The Industrial Centre for Geological Disposal in France, fragments of paintings by Lithuanian symbolist M. K. Čiurlionis, Cold War-era television and radio footage, computer-generated 3D images of atoms and uranium ore, and ambient music, can stimulate emotional and intellectual responses to its subject, even though there are no characters to identify with and no clear plot or strong rhetorical devices to direct the viewer. The use of immersive technologies in Škarnulytė’s film creates the sense of a “living” environ- ment experienced in “real time,” drawing on terms introduced by Oliver Grau (2003). The article’s conclusions are based on a close examination of the film’s style and narrative, as well as theoretical work on immersive films and media by Oliver Grau (2003) and Kerric Harvey (2012). The concepts of ecocinema (Paula Willoquet-Maricondi, 2010), eco-cosmopolitan cinema (Ursula K. Heise, 2008), and the essay film (Laura Rascaroli, 2017) are chosen as the theoretical framework for analysing Burial.

Ethics Concerns in the Use of Computer-Generated Images for Human Communication

The rapid growth of artificial intelligence (AI) tools has contributed to various image-generation techniques. These tools have had a significant effect on how we perceive contemporary communication. This study presents a broad overview of the challenges and consequences associated with the influence of AI on communication, and its findings are supported by thoughts collected from various books and academic publications. Nevertheless, incorporating AI into communication through synthetic imagery raises concerns about communication that require careful consideration. This study investigates various ethical concerns and the significance of ethical guidelines and responsible practices in creating these applications. It intricately weaves together philosophical reflections, ethical deliberations, and societal responsibilities, shedding light on the complex interplay between ethics, technology, and human values within the context of machine development and broader societal realms.

Developing augmented reality filters to display visual cues on diverse skin tones

Introduction: Variations in skin tone can significantly alter the appearance of symptoms such as rashes or bruises. Unfortunately, previous works utilizing Augmented Reality (AR) in simulating visual symptoms have often failed to consider this critical aspect, potentially leading to inadequate training and education. This study seeks to address this gap by integrating generative artificial intelligence (AI) into the AR filter design process.Methods: We conducted a 2 × 5 within-subjects study with second-year nursing students (N = 117) from the University of Florida. The study manipulated two factors: symptom generation style and skin tone. Symptom generation style was manipulated using a filter based on a real symptom image or a filter based on a computer-generated symptom image. Skin tone variations were created by applying AR filters to computer-generated images of faces with five skin tones ranging from light to dark. To control for factors like lighting or 3D tracking, 101 pre-generated images were created for each condition, representing a range of filter transparency levels (0–100). Participants used visual analog scales on a computer screen to adjust the symptom transparency in the images until they observed image changes and distinct symptom patterns. Participants also rated the realism of each condition and provided feedback on how the symptom style and skin tone impacted their perceptions.Results: Students rated the symptoms displayed by the computer-generated AR filters as marginally more realistic than those displayed by the real image AR filters. However, students identified symptoms earlier with the real-image filters. Additionally, SET-M and Theory of Planned Behavior questions indicate that the activity increased students’ feelings of confidence and self-efficacy. Finally, we found that similar to the real world, where symptoms on dark skin tones are identified at later stages of development, students identified symptoms at later stages as skin tone darkened regardless of cue type.Conclusion: This work implemented a novel approach to develop AR filters that display time-based visual cues on diverse skin tones. Additionally, this work provides evidence-based recommendations on how and when generative AI-based AR filters can be effectively used in healthcare education.

Augmented Reality Applications in Mechanical System Design and Prototyping

With the integration of computer-generated images and data into the real world, augmented reality (AR) is a game-changing technology that improves users' perceptions and interactions with their surroundings. This technology, which can overlay digital data on real-world environments, has great potential for use in several fields, such as mechanical system design and prototyping. The use of AR in this industry is not just a theoretical idea; rather, it is a rapidly developing reality with enormous potential for creativity, effectiveness, and accuracy. Augmented Reality (AR) is a technology that combines the physical and digital worlds to provide a composite vision that improves the user's sense of reality. Augmented Reality (AR) superimposes digital data in real-time over the actual world, in contrast to Virtual Reality (VR), which submerges users in a fully digital environment. Usually, gadgets like tablets, smartphones, AR glasses, and head-mounted displays (HMDs) help with this integration. The term "mechanical system design" describes the entire process of imagining, creating, and perfecting mechanical parts and systems; it includes everything from rough concept drawings to intricate engineering models and simulations. Before moving on with full-scale manufacturing, prototyping entails building early models or samples of a product to test and verify design concepts.

Notes On Artificial Intelligence And The Rise Of New Images

Pamela Breda’s (Digital Arts) contribution "Notes On Artificial Intelligence And The Rise Of New Images" explores how hyper-realistic computer-generated images (CGI) reshape our perception of reality and its implications for human creativity. Her considerations stem from an ongoing interdisciplinary artistic research project that combines positions from visual cultural studies, cognitive psychology, and perceptual theory with historical perspectives. Breda’s contribution reflects on the historical background of CGI, its influence on various domains of individual and collective life, and its philosophical implications, her contribution provides current viewpoints on the position of AI and its past implications.

Smart city VR landscape planning and user virtual entertainment experience based on artificial intelligence

Smart city VR landscape planning and user virtual entertainment experience based on artificial intelligence

The effect of islamic ornament as secondary skin on daylight quality

Abstract Islamic ornaments are used extensively in different types of buildings, serving both aesthetic and functional purposes. They are used in mosques, offices and other buildings, serving as both interior and exterior elements. One application is their use as secondary skins to cover window openings. This research investigates the effect of Islamic ornaments as secondary skins on interior lighting. The main question addressed is how Islamic ornaments affect the quality of natural lighting. Using computer simulations, scenarios with clear glass and varying ornament distance from the window were assessed under clear sky conditions at different times of the day. The results show that the presence of Islamic ornaments significantly reduces the average daylighting level on interior surfaces compared to scenarios without ornaments. Visual representations using ray diagrams and computer-generated images illustrate the effects of varying ornamental conditions. This research highlights the potential of Islamic ornaments to improve the quality of daylighting in architecture. The findings emphasise their role in optimising daylight indoors, and encourage careful consideration of the impact of spacing on window openings. In particular, the distribution of daylight varies between rooms orientated to the north and west.

Conspicuity of staircase configuration: Effects of markings and contrast.

To be able to walk safely up or down a staircase, we must be able to judge the configuration and slope of the staircase and our viewing position. Adding markings to the stairs might help form correct perceptions of the staircase geometry. In this study, we examined how visual judgements about staircase configuration are affected by different marking patterns. Fifteen normally sighted young participants viewed computer-generated images of staircases as seen from the top landing of the stairs. Marking patterns included contrasting baseboard, transverse edge-stripes, longitudinal side-stripes, longitudinal stripes, diamond patterns, longitudinal stripes extended to landing and diamond patterns extended to landing. For comparison, we included the no-marking condition as a control. We tested several contrast levels of marking patterns (3.2%-50%), pitch lines of the staircases (shallow/medium/steep) and viewing positions (left/centre/right). The effect of the overall shape cue of the staircase on participants' performance was also evaluated. We measured participants' accuracies in judging whether the staircase was shallow, medium or steep, and whether the viewing position was located to the left, centre or right. Transverse edge-stripes markings yielded fewer underestimations of slope (9% [transverse] vs. 18% [others]) when compared with other markers. The presence of an overall shape cue helped both slope (67% [presence] vs. 51% [absence]) and viewing position judgements (79% [presence] vs. 62% [absence]). When the overall shape cue was present, only the transverse edge-stripes markings yielded a significant improvement in performance (compared with no-marking condition). When the cue was absent, performance was significantly better with markings with high and moderate contrasts. Adding marking patterns such as high-contrast transverse stripes to stairs may help enhance the visibility of the stairs and judgements of staircase geometry. This might be particularly useful for people with visual impairment or normally sighted individuals under compromised environmental conditions.

O04 Delineation of psoriasis from uninvolved skin using an artificial neural network as a means of targeting phototherapy to psoriatic lesions

Abstract Introduction and aims Narrowband ultraviolet B therapy (NB-UVB) is an effective treatment for psoriasis. Currently, NB-UVB is delivered in whole-body cabinets to all of the patient’s skin, thus increasing the risk of normal skin sunburning and the potential risk of skin cancer development. This limits the NB-UVB doses that can be used and requires patients attend sessions three times weekly for up to 10 weeks in order to complete treatment. An artificial intelligence (AI)-mediated, targeted NB-UVB approach would avoid these risks and allow use of higher NB-UVB doses for the areas of the skin affected by psoriasis. We sought to train an artificial neural network on digital images of psoriasis, and subsequently test this trained model in order to assess its accuracy at distinguishing psoriasis from unaffected skin. Methods Overall, 104 digital images of psoriasis from 14 patients with this skin condition, who attended the dermatology department at University Hospital Southampton NHS Foundation Trust, were used to train a conditional generative adversarial network– ‘pix2pix’. Areas of psoriasis were delineated within the images prior to the images being augmented by randomly cropping, rotating and altering colour intensity, thereby increasing the total number to 23 111 images to train and test the neural network. Results The trained neural network was able to identify psoriasis in unseen digital images with 96.73% accuracy at the pixel level across the dataset. The output of the neural network (i.e. a computer-generated image of psoriasis) acted as a signal source for a digital micromirror device (DMD) that was able to shape visible light and project this light over the original image of psoriasis, while avoiding the uninvolved skin. Conclusions It is possible to differentiate psoriasis from unaffected skin within digital images using an artificial neural network. We demonstrated that AI-mediated targeted phototherapy using a DMD is feasible.

The Review of Modeling and Rendering 3D Environment: A Survey

This paper explores several topics in the field of 3D Environments, including ray tracing, rendering techniques, algorithms and optimization, data processing, real-time rendering, modeling, physical simulation, and material modeling. The paper covers a large variety of applications and techniques that are widely used in computer graphics and visualization. This paper also points out that significant progress has been made in ray tracing, texture filtering, image processing, motion synthesis, geometric modeling, and physical simulation. These advances have improved the visual quality, performance, and fidelity of computer-generated images. In addition, the article mentions the trend of integrating machine learning, deep learning, and data analysis techniques into computer graphics and visualization, especially in data processing and analysis models, to improve the results of rendering and simulation. Overall, this article explores details of the current state of the computer graphics and visualization field, highlighting the various technologies and applications which shapes the field.

Physics Based Animation Using Computer Graphics

Physics-based animation is a multidisciplinary area that uses ideas from physics, computer science, and mathematics to create realistic and dynamic movements in virtual settings. The basic ideas and methods of physics-based animation are introduced in this research paper, with an emphasis on how mathematical models and physical laws are used to produce realistic motion in computer-generated images. To construct realistic virtual environments, key disciplines covered include fluid simulation, fabric simulation, rigid body dynamics, and soft body dynamics. The report highlights recent developments in real-time physics simulations and addresses other topics such as processing economy, accuracy, and scalability. Applications for physics-based animation can be found in many different fields, such as virtual reality, simulation training, movies, and video games. The pursuit of more precise and effective physics-based animation is essential as technology develops to produce captivating and realistic virtual worlds. Keywords— Physics-based animation(PBA), virtual environment, Physics simulation, Dynamics, Animation software, Real-time physics, Collision detection, Fluid dynamics, Particle systems, Cloth simulation, Smooth particle hydrodynamics, finite element method, Navier-Stokes, Rigid body dynamics, Soft body dynamics, Deformation, Motion capture, Character animation, Kinematics, Rendering, Game development, Virtual reality, Augmented reality, Computer graphics, Simulation accuracy

A Comprehensive Exploration of Fidelity Quantification in Computer-Generated Images.

Generating realistic road scenes is crucial for advanced driving systems, particularly for training deep learning methods and validation. Numerous efforts aim to create larger and more realistic synthetic datasets using graphics engines or synthetic-to-real domain adaptation algorithms. In the realm of computer-generated images (CGIs), assessing fidelity is challenging and involves both objective and subjective aspects. Our study adopts a comprehensive conceptual framework to quantify the fidelity of RGB images, unlike existing methods that are predominantly application-specific. This is probably due to the data complexity and huge range of possible situations and conditions encountered. In this paper, a set of distinct metrics assessing the level of fidelity of virtual RGB images is proposed. For quantifying image fidelity, we analyze both local and global perspectives of texture and the high-frequency information in images. Our focus is on the statistical characteristics of realistic and synthetic road datasets, using over 28,000 images from at least 10 datasets. Through a thorough examination, we aim to reveal insights into texture patterns and high-frequency components contributing to the objective perception of data realism in road scenes. This study, exploring image fidelity in both virtual and real conditions, takes the perspective of an embedded camera rather than the human eye. The results of this work, including a pioneering set of objective scores applied to real, virtual, and improved virtual data, offer crucial insights and are an asset for the scientific community in quantifying fidelity levels.

On the Social Media Platform, Virtual Internet Celebrities and Real Idol Brand Spokesmen Perceive Human Nature, Physical Charm, and Study Consumer Reaction Based on Self-Consistency: The Media Effect of Trust

With technological advances in computer-generated images, a new type of social media influencer has arisen, the virtual webcam. It has an advantage over human webmasters because, without physical constraints, their images are easier to control. However, it remains to be seen and researched whether virtual influencers can be as effective as human influencers in generating positive brand attitudes. Virtual web celebrities or real idols, marketing to consumers is the trust of the marketing effect, so it tries to discuss from the empirical. This paper discusses the role of perceiving human nature, charm, and the mediation effect of trust based on self-consistency. To this end, determine the perception of human-level (high/low) and charm (high/low) self-consistency (high/low) model spokesperson type (virtual web celebrity/real idol) on the influence of advertising effect, the results show that consumers to brand perception human nature and charm level is higher, when a positive attitude towards advertising and high trust, and consumer self-consistency is higher brand spokesperson also have higher preference. In addition, trust also plays a media role in the relationship between the characteristics of brand spokesmen and the advertising effect. Specifically, when the level of human nature and charm is high, the spokesperson will be more trustworthy, which also has a positive impact on the effect of all advertising. Finally, the influence of human nature perception and charm on the advertising effect does not change according to the different types of spokesmen, but in contrast, the trust degree of real idol models is higher than that of virtual web celebrities, and their positive attitude and purchase intention to the brand are also higher. Perception of humanity, charm, and self-consistency all have a positive impact on trust. Furthermore, trustworthiness had a meaningful effect on consumer response and was confirmed to have a vector effect on all independent variables. This study is expected to provide both theoretical and practical value by clarifying the effects of the main variables that may influence the marketing of brand spokesmen.

Detect with Style: A Contrastive Learning Framework for Detecting Computer-Generated Images

The detection of computer-generated (CG) multimedia content has become of utmost importance due to the advances in digital image processing and computer graphics. Realistic CG images could be used for fraudulent purposes due to the deceiving recognition capabilities of human eyes. So, there is a need to deploy algorithmic tools for distinguishing CG images from natural ones within multimedia forensics. Here, an end-to-end framework is proposed to tackle the problem of distinguishing CG images from natural ones by utilizing supervised contrastive learning and arbitrary style transfer by means of a two-stage deep neural network architecture. This architecture enables discrimination by leveraging per-class embeddings and generating multiple training samples to increase model capacity without the need for a vast amount of initial data. Stochastic weight averaging (SWA) is also employed to improve the generalization and stability of the proposed framework. Extensive experiments are conducted to investigate the impact of various noise conditions on the classification accuracy and the proposed framework’s generalization ability. The conducted experiments demonstrate superior performance over the existing state-of-the-art methodologies on the public DSTok, Rahmouni, and LSCGB benchmark datasets. Hypothesis testing asserts that the improvements in detection accuracy are statistically significant.