Visual Realism Research Articles

Psicología y literatura: algunas reflexiones sobre Doña rosita la soltera de García Lorca

Introduction: This study presents one of the 20th century’s most original and complex figures, writer Federico García Lorca (1898-1936). Through an in-depth psychological analysis of Lorca’s poetics, particularly his drama Doña Rosita la Soltera, the study aims to show that the characters created by Lorca may represent fragmented aspects of his own personality that project themselves, even unconsciously, onto the narrative. Methodology: The approach is based on the Psychology of Art and Literature, as developed by Professor Antonio Fusco, which involves investigating the psychological motivations behind the author’s creation of specific characters and scenarios. Results: The analysis reveals the impact of key life episodes on García Lorca, profoundly influencing his thoughts and leading to a realistic and pessimistic worldview. Discussion: Critical interpretative reflections are provided throughout, exploring the thematic opposition of Eros and Thanatos as essential to Lorca’s narrative. Conclusions: The study concludes that Lorca’s personal experiences significantly shaped his worldview, rendering it fragile and deeply infused with a stark vision of reality.

Artificial Intelligence Scene Creation with Virtual Technology for the DigitalFilm

Artificial Intelligence-based scene creation leverages advanced algorithms to generate realistic and immersive environments for various applications, including gaming, virtual reality, and simulations. By utilizing techniques such as procedural generation, deep learning, and computer vision, these systems can automatically create complex landscapes, detailed textures, and dynamic elements that respond to user interactions. This not only enhances the user experience but also significantly reduces the time and effort required for manual scene design, enabling developers to focus on creativity and innovation. In the realm of digital media production, the quest for lifelike scenes and efficient evaluation methodologies has led to the exploration of novel techniques. This paper investigates the synergy between point estimation and artificial intelligence (AI) in advancing digital scene creation and evaluation. Through comprehensive simulations and analyses, we assess the effectiveness of point estimation in quantifying scene attributes such as visual realism, dynamic interactivity, physical accuracy, and artistic expression. Additionally, we delve into the utilization of AI algorithms for automating scene classification, thereby streamlining decision-making processes and optimizing resource allocation in production workflows. Through comprehensive simulations and analyses, we assess the effectiveness of point estimation in quantifying scene attributes such as visual realism (mean score: 0.85), dynamic interactivity (mean score: 0.72), physical accuracy (mean score: 0.93), and artistic expression (mean score: 0.65).

Nowy wygładzony świat. Zmysł estetyki w dobie AI

The surprising speed of new technological progress leaves us guessing. It is worth asking questions about the consequences of AI development in the context of our aesthetic sense. Do AI and algorithms affect our perception of beauty? We already know that the filters in smartphones have a negative impact on the self-image of young generations. What happens, when the media are dominated by the “ideal” images generated by Mid Journey and Dall-e? What vision of reality do we create for the next generations and how to keep a human element in such a smoothed world? The AI aesthetic is visible not only in generated images, but also in texts generated by AI language models. It is omnipresent. Early consideration of pros and cons of AI in the context of shaping the aesthetic sense of the contemporary society gives us a chance to avoid some risks and use its potential instead. Keywords: new technologies, algorithms, artificial intelligence (AI), AI aesthetic, consequences of AI development

O vztahu Patočkovy filosofie k filosofii Jaspersově

In the first part, the author sketches the problem of human existence as it appears in the texts of both philosophers. The second part enumerates all Patočka’s texts mentioning Jaspers as well as all of the works by Jaspers that we know Patočka reflected on. The third part traces in more detail Jaspers’ book Philosophical Faith, in which Patočka, in his own words, found “great stimuli”, and shows several links between Patočka’s own philosophy and the book (especially four themes: the relation between philosophy and science; between philosophy and revealed religion; between philosophy and “non-philosophy”; between philosophy and history). The fourth part traces the idea of the origin of the free human act, which was explored by both Patočka and Jaspers. Finally, the article shows that despite similar or even identical lines of thought on certain topics – including a topic as fundamental as human freedom –, the authors offer two fundamentally different visions of reality that could be labelled as “ontology vs. metaphysics” or “the totality of the world vs. extra-worldly transcendence”.

Visual realism and character identification in science comics: an empirical study testing McCloud’s ‘masking effect’ theory

Visual realism and character identification in science comics: an empirical study testing McCloud’s ‘masking effect’ theory

Reference ranges and test-retest reliability of subject visual horizontal from different head-tilt angles in young healthy adults

Objective:To establish the normal values of subjective visual horizontal（SVH） under different head tilt angles, analyze the test-retest reliability, and provide a normal value reference for the refined diagnosis and functional assessment of SVH in clinical vestibular disorders. Methods:Thirty-one healthy young people were selected to wear visual reality glasses to test SVH data in five different head tilt angles: upright head position 0°, head tilted 45°to the left（L45°）, head tilted 45° to the right（R45°）, head tilted 90° to the left（L90°）, and head tilted 90° to the right（R90°）, and were re-tested 2 weeks later. Results:①The normal values of SVH at 0°, L45°, R45°, L90°, and R90°were 0.30±1.32, 5.94±5.54, -11.44±5.32, -0.87±8.63, -2.70±8.02, respectively. ②The 95% confidence intervals of SVH at 0°, L45°, R45°, L90°, and R90° were: （-2.34,2.94）,（-5.14,17.02）,（-22.08,-0.80）,（-18.13,16.39）,（-18.74，13.34）, respectively. The ratio of asymmetry in the absolute value of bilateral 45° deviation was 26.4% and the ratio of asymmetry in the absolute value of bilateral 90° deviation was 1.3%. ③The intra-class correlation coefficient（ICC） for 0°, L45°, R45°, L90° and R90° was 0.625, 0.641, 0.564, 0.769, 0.656, respectively. Conclusion:SVH has good test-retest reliability and high clinical test stability and stability. The data on normal values of SVH at different head tilt angles established in this study can provide clinical references for the refined diagnosis and functional assessment of vestibular system disorders.

Executing realistic earthquake simulations in unreal engine with material calibration

Earthquakes significantly impact societies and economies, underscoring the need for effective search and rescue strategies. As AI and robotics increasingly support these efforts, the demand for high-fidelity, real-time simulation environments for training has become pressing. Earthquake simulation can be considered as a complex system. Traditional simulation methods, which primarily focus on computing intricate factors for single buildings or simplified architectural agglomerations, often fall short in providing realistic visuals and real-time structural damage assessments for urban environments. To address this deficiency, we introduce a real-time, high visual fidelity earthquake simulation platform based on the Chaos Physics System in Unreal Engine, specifically designed to simulate the damage to urban buildings. Initially, we use a genetic algorithm to calibrate material simulation parameters from Ansys into the Unreal Engine’s fracture system, based on real-world test standards. This alignment ensures the similarity of results between the two systems while achieving real-time capabilities. Additionally, by integrating real earthquake waveform data, we improve the simulation’s authenticity, ensuring it accurately reflects historical events. All functionalities are integrated into a visual user interface, enabling zero-code operation, which facilitates testing and further development by cross-disciplinary users. We verify the platform’s effectiveness through three AI-based tasks: similarity detection, path planning, and image segmentation. This paper builds upon the preliminary earthquake simulation study we presented at IMET 2023, with significant enhancements, including improvements to the material calibration workflow and the method for binding building foundations.

Memory-Based Learning and Fusion Attention for Few-Shot Food Image Generation Method

Generating food images aims to convert textual food ingredients into corresponding images for the visualization of color and shape adjustments, dietary guidance, and the creation of new dishes. It has a wide range of applications, including food recommendation, recipe development, and health management. However, existing food image generation models, predominantly based on GANs (Generative Adversarial Networks), face challenges in maintaining semantic consistency between image and text, as well as achieving visual realism in the generated images. These limitations are attributed to the constrained representational capacity of sparse ingredient embedding and the lack of diversity in GAN-based food image generation models. To alleviate this problem, this paper proposes a food image generation network, named MLA-Diff, in which ingredient and image features are learned and integrated as ingredient-image pairs to generate initial images, and then image details are refined by using an attention fusion module. The main contributions are as follows: (1) The enhanced CLIP (Contrastive Language-Image Pre-Training) module is constructed by transforming sparse ingredient embedding into compact embedding and capturing multi-scale image features, providing an effective solution to alleviate semantic consistency issues. (2) The Memory module is proposed by embedding a pre-trained diffusion model to generate initial images with diversity and reality. (3) The attention fusion module is proposed by integrating features from diverse modalities to enhance the comprehension between ingredient and image features. Extensive experiments on the Mini-food dataset demonstrate the superiority of the MLA-Diff in terms of semantic consistency and visual realism, generating high-quality food images.

Neural network reconstruction of the left atrium using sparse catheter paths.

Catheter-based radiofrequency ablation for pulmonary vein isolation has become the first line of treatment for atrial fibrillation in recent years. This requires a rather accurate map of the left atrial sub-endocardial surface including the ostia of the pulmonary veins, which requires dense sampling of the surface and currently takes more than 10min. The focus of this work is to provide left atrial visualization early in the procedure to ease procedure complexity and enable further workflows, such as using catheters that have difficulty sampling the surface. We propose a dense encoder-decoder network with a novel regularization term to reconstruct the shape of the left atrium from partial data which is derived from simple catheter maneuvers. To train the network, we acquire a large dataset of 3D atria shapes and generate corresponding catheter trajectories, from which traversed point clouds are obtained. Once trained, we show that the suggested network can sufficiently approximate the atrium shape based on a given trajectory. We compare several network solutions for the 3D atrium reconstruction. We demonstrate that the solution proposed produces realistic visualization using partial acquisition within a 3-min time interval using human clinical cases.

No effect of reducing visual realism on motion sickness in virtual reality

No effect of reducing visual realism on motion sickness in virtual reality

SP1.13 - An Overview of Laparoscopic Surgical Training Modalities – How Does Augmented Reality Simulation Compare?

Abstract Background Laparoscopic surgery is known to require intensive training to gain the required skills and with the increasing popularity of laparoscopic surgery over open surgery requires novel and efficient ways of training. AR is a novel introduction to laparoscopic surgical training and can superimpose digital images and physical models with the unique advantage of combining visual realism with true-to-life haptic feedback. Methods Compare different types of laparoscopic training modalities and assess how AR compares to the education system, 31 papers were systematically reviewed, and the findings were compiled. Results Both the available products as well as the technology as an educational modality were evaluated. Results Studies reported relatively increased speed of learning, improved ability to multitask, procedural accuracy, hand-eye coordination and bimanual operation in a reduced practice time and increased success rate with AR in healthcare education. One of the limitations of AR is that it doesn’t reflect the non-technical skills required in the operation. Compared with other modalities AR provided faster skill acquisition and was widely preferred, except when compared against a human cadaver model for straight laparoscopic colorectal skills acquisition. AR tends to have a higher initial purchasing cost but does not require the costly specialist facilities or services that cadaver or animal models do, 150 trusts in the NHS preliminary data is showing an estimated annual saving of £117m. Conclusion AR simulation has the potential to become the new gold standard for laparoscopic surgical training, and beyond, pending further development of literature to increase knowledge of the technology and its capabilities, on top of technological evolution to increase clinical realism.

ETBHD‐HMF: A Hierarchical Multimodal Fusion Architecture for Enhanced Text‐Based Hair Design

AbstractText‐based hair design (TBHD) represents an innovative approach that utilizes text instructions for crafting hairstyle and colour, renowned for its flexibility and scalability. However, enhancing TBHD algorithms to improve generation quality and editing accuracy remains a current research difficulty. One important reason is that existing models fall short in alignment and fusion designs. Therefore, we propose a new layered multimodal fusion network called ETBHD‐HMF, which decouples the input image and hair text information into layered hair colour and hairstyle representations. Within this network, the channel enhancement separation (CES) module is proposed to enhance important signals and suppress noise for text representation obtained from CLIP, thus improving generation quality. Based on this, we develop the weighted mapping fusion (WMF) sub‐networks for hair colour and hairstyle. This sub‐network applies the mapper operations to input image and text representations, acquiring joint information. The WMF then selectively merges image representation and joint information from various style layers using weighted operations, ultimately achieving fine‐grained hairstyle designs. Additionally, to enhance editing accuracy and quality, we design a modality alignment loss to refine and optimize the information transmission and integration of the network. The experimental results of applying the network to the CelebA‐HQ dataset demonstrate that our proposed model exhibits superior overall performance in terms of generation quality, visual realism, and editing accuracy. ETBHD‐HMF (27.8 PSNR, 0.864 IDS) outperformed HairCLIP (26.9 PSNR, 0.828 IDS), with a 3% higher PSNR and a 4% higher IDS.

Image inpainting algorithm based on inference attention module and two-stage network

Current image inpainting techniques often yield distorted structures or blurred textures that clash with the surrounding context, particularly when addressing extensive missing regions or highly textured images. These methods often struggle to reconstruct realistic and coherent image structures. To address this challenge, we introduce a two-stage network image restoration approach that leverages an inferential attention mechanism. In the first stage, an edge generation network is employed to produce plausible phantom edge information. Subsequently, an image complementation network is utilized to complete the image restoration process. To enhance the visual realism and restoration accuracy of the generated images, we incorporate an inferential attention mechanism within the image complementation network. This mechanism effectively mitigates inconsistencies in the generated features, leading to the production of more meaningful and effective information. We evaluate our proposed method on benchmark datasets, including Places2 dataset, CelebFaces Attributes dataset, and Paris StreetView dataset. The experimental results can demonstrate that the proposed method achieves better Structural Similarity Index and Peak Signal-to-noise Ratio than others. These metrics indicate superior performance compared to existing image inpainting methods, delivering higher image inpainting accuracy and more realistic image reconstruction effect.

Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI.

Adversarial training has attracted much attention in enhancing the visual realism of images, but its efficacy in clinical imaging has not yet been explored. This work investigated adversarial training in a clinical context, by training 206 networks on the OASIS-1 dataset for improving low-resolution and low signal-to-noise ratio (SNR) magnetic resonance images. Each network corresponded to a different combination of perceptual and adversarial loss weights and distinct learning rate values. For each perceptual loss weighting, we identified its corresponding adversarial loss weighting that minimized structural disparity. Each optimally weighted adversarial loss yielded an average SSIM reduction of 1.5%. We further introduced a set of new metrics to assess other clinically relevant image features: Gradient Error (GE) to measure structural disparities; Sharpness to compute edge clarity; and Edge-Contrast Error (ECE) to quantify any distortion of the pixel distribution around edges. Including adversarial loss increased structural enhancement in visual inspection, which correlated with statistically consistent GE reductions (p-value << 0.05). This also resulted in increased Sharpness; however, the level of statistical significance was dependent on the perceptual loss weighting. Additionally, adversarial loss yielded ECE reductions for smaller perceptual loss weightings, while showing non-significant increases (p-value >> 0.05) when these weightings were higher, demonstrating that the increased Sharpness does not adversely distort the pixel distribution around the edges in the image. These studies clearly suggest that adversarial training significantly improves the performance of an MRI enhancement pipeline, and highlights the need for systematic studies of hyperparameter optimization and investigation of alternative image quality metrics.

Tire Texture Monitoring (VGG 19 VS Efficient Net b7)

Tires are crucial components of vehicles, continuously in contact with the road. Monitoring tire conditions is vital for safety and performance, as degradation in tire treads and sidewalls can affect traction, fuel efficiency, longevity, and road noise. This research leverages both VGG19 and Efficient Net B7 algorithms to enhance tire image rendering, addressing limitations of traditional techniques. Using a binary classification algorithm, we classify tire images as healthy or cracked. By fine-tuning VGG19 and EfficientNet B7 on a specialized tire dataset, we achieve high-quality, photorealistic renderings. Our results demonstrate remarkable improvements in texture quality and visual realism compared to traditional methods. The rendered images exhibit finer details and more accurate representations of the tire’s tread patterns and material properties. This research contributes to the field of computer graphics by presenting a novel application of deep learning techniques to a specific industrial need, paving the way for future advancements in high-quality rendering of complex tire textures. Key Words: VGG19,Photorealistic rendering, deep learning.

“You Are Not the Victim Here”: Conspirituality and the Framing of Evangelical Patriarchy as a Victim of #ChurchToo Disruption

ABSTRACT The term “Church Too” not only echoes “#MeToo” but implies a rebuttal against American evangelicalism’s authoritative and longstanding argument of the church existing as a safe and divinized place and the churchgoer positioned within a secure environment – unable to be a part of a sexual assault experience. In other words, abuse happens in “Church Too.” In this piece, we argue that churches’ rhetorical responses to the #ChurchToo movement should be understood as part of evangelicalism’s ongoing perception of being under attack from feminism. They are, therefore, victims in the culture war, in which “ChurchToo” becomes yet another battle to be fought, with the church taking defense. Consequently, evangelicalism’s defense narratives use strategies of conspirituality, narratives of disruption, and the victimhood enthymeme. As a result, we argue scholars must consider these rhetorical strategies to understand how the ideology of victimhood is both deeply embedded and an exceedingly powerful vision of reality, within white American evangelicalism.

A new model of electrosurgical tissue damage for neurosurgery simulation

BackgroundBipolar hemostasis electrocoagulation is a fundamental procedure in neurosurgery. A precise electrocoagulation model is essential to enable realistic visual feedback in virtual neurosurgical simulation. However, existing models lack an accurate description of the heat damage and irreversible tissue deformation caused by electrocoagulation, thus diminishing the visual realism. This work focuses on the electrocoagulation model for neurosurgery simulation. MethodIn this paper, a position-based dynamics (PBD) model with a bioheat transfer and damage prediction (BHTDP) method is developed for simulating the deformation of brain tissue caused by electrocoagulation. The presented BTHDP method uses the Arrhenius equation to predict thermal damage of brain tissue. A deformation model with energy and thermal damage constraints is developed to characterize soft tissue deformation during heat absorption before and after thermal injury. Visual effect of damaged brain tissue is re-rendered. ResultTo evaluate the accuracy of the proposed method, numerical simulations were conducted and compared with commercial finite element software. The maximum normalized error of the proposed model for predicting midpoint temperature is 10.3 % and the maximum error for predicting the thermal damage is 5.4 %. The contraction effects of heat-exposed anisotropic tissues are also simulated. The results indicate that the presented electrocoagulation model provides stable and realistic visual effects, making it applicable for simulating the electrocoagulation process in virtual neurosurgery.

862 An Overview of Laparoscopic Surgical Training Modalities – How Does Augmented Reality Simulation Compare?

Abstract Aim Compare different types of laparoscopic training modalities and assess how AR compares to the education system using the apprenticeship model on patients and alternative training modalities, including human cadavers, box trainers, and virtual reality (VR) simulators. AR is a novel introduction to laparoscopic surgical training and can superimpose digital images and physical models with the unique advantage of combining visual realism with true-to-life haptic feedback. Method 31 papers were systematically reviewed, and the findings were compiled. Results for the available products and the technology as an educational modality were evaluated. Results Studies reported increased speed of learning, improved ability to multitask, procedural accuracy, hand-eye coordination and bimanual operation in a reduced practice time and increased success rate with AR in healthcare education. One of the limitations of AR it doesn’t reflect the non-technical skills required in the operation. Compared with other modalities AR provided faster skill acquisition and was widely preferred, except when compared to the cadaver model for straight laparoscopic colorectal skills acquisition. AR tends to have a higher initial purchasing cost but does not require the costly specialist facilities or services that cadaver or animal models do, 150 trusts in the NHS preliminary data show an estimated annual saving of £117m. Conclusions AR simulation has the potential to become the new gold standard for laparoscopic surgical training, and beyond, pending further development of literature to increase knowledge of the technology and its capabilities, on top of technological evolution to increase clinical realism.

Modeling Realistic Clothing From a Single Image Under Normal Guide.

We propose a robust and highly realistic clothing modeling method to generate a 3D clothing model with visually consistent clothing style and wrinkles distribution from a single RGB image. Notably, this entire process only takes a few seconds. Our high-quality clothing results benefit from the idea of combining learning and optimization, making it highly robust. First, we use the neural networks to predict the normal map, a clothing mask, and a learning-based clothing model from input images. The predicted normal map can effectively capture high-frequency clothing deformation from image observations. Then, by introducing a normal-guided clothing fitting optimization, the normal maps are used to guide the clothing model to generate realistic wrinkles details. Finally, we utilize a clothing collar adjustment strategy to stylize clothing results using predicted clothing masks. An extended multi-view version of the clothing fitting is naturally developed, which can further improve the realism of the clothing without tedious effort. Extensive experiments have proven that our method achieves state-of-the-art clothing geometric accuracy and visual realism. More importantly, it is highly adaptable and robust to in-the-wild images. Further, our method can be easily extended to multi-view inputs to improve realism. In summary, our method can provide a low-cost and user-friendly solution to achieve realistic clothing modeling.

Creation of a Novel Ex Vivo 3D Printed Ileal Conduit Task Trainer for Teaching Conduitoscopy Skills

ObjectivesTo perform endoscopy in patients with urinary diversions requires specific endoscopic skills, which can currently only be gained in clinical practice. We created a 3D printed ex vivo ileal conduit model (stoma and conduit with ureters and 2 kidneys) to simulate “conduitoscopy” and evaluated the realism and limitations of the model. MethodsAccurate anatomical features were represented using an appropriate reusable design, realistic mechanical qualities with several material types, and 3D-printed components. Different models of bowel and ureters were assessed by the subject-matter experts (SME). The final ileal conduit model (Wallace 1 type anastomosis) was evaluated by 18 SMEs. ResultsMost experts gave their approval to the view of the stoma, as well as the appearance of the bowel, ureteric, and pelvicalyceal systems. A total of 72.1% of SMEs approved the ureteric endoscopic view compared to about 66% who accepted the endoscopic examination of the bowel. The model's overall appearance was good for 61.1% and excellent for 38.8% of experts. ConclusionConduitoscopy simulation training can now be facilitated using our novel and unique cutting-edge 3D printed model. We created a model that is highly anatomically accurate and workable. In our study, anatomical and visual realism was demonstrated. The next step would be increasing the length of the conduit and conduct a validation study.