Search

The authors propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here further comes from intuitive object selection and real‐time editing. To achieve this, Gaussian Splatting Radiance Field is adopted as the scene representation and its explicit nature and speed advantage are fully leveraged. Its explicit representation formulation allows to devise a 2D prompt points to 3D masks dual‐stage self‐prompting segmentation algorithm, perform mask refinement and merging, minimize changes, and provide good initialization for scene inpainting and perform editing in real‐time without per‐editing training; all lead to superior quality and performance. The method was tested by editing both forward‐facing and 360 scenes. The method is also compared against existing methods, showing superior quality despite being more capable and having a speed advantage. [ABSTRACT FROM AUTHOR]

Abstract The authors propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here further comes from intuitive object selection and real‐time editing. To achieve this, Gaussian Splatting Radiance Field is adopted as the scene representation and its explicit nature and speed advantage are fully leveraged. Its explicit representation formulation allows to devise a 2D prompt points to 3D masks dual‐stage self‐prompting segmentation algorithm, perform mask refinement and merging, minimize changes, and provide good initialization for scene inpainting and perform editing in real‐time without per‐editing training; all lead to superior quality and performance. The method was tested by editing both forward‐facing and 360 scenes. The method is also compared against existing methods, showing superior quality despite being more capable and having a speed advantage.

The present study shows the development of computational algorithms to represent aircraft instruments such as the attitude indicator or the turn-and-slip indicator; moreover, the algorithms represent a magnetic compass and other instruments that function according to other physical theories. These instruments work by using the gyroscope and magnetic principles and help the pilot in navigation. These are considered to be the basic instruments required to provide location-related and positional information about the actual aircraft attitude. The algorithms developed in this study are capable of working in concordance with other instruments and the physical conditions established. The programming language used was C++ and the algorithms were compiled in independent files and subroutines for computational efficiency, eliminating unnecessary code. The display options were successfully tested. Additionally, an analysis that evaluated the error and approached flight simulation as a function of step time (Δt) is also described. [ABSTRACT FROM AUTHOR]

The study aimed to ascertain how learners' performance in the chemical hybridization concept was affected by the Computer Animation Instructional Package (CAI). A pretest-posttest quasi-experimental research design was used in the study. There were 120 seniors secondary school students in the sample. The control group received instruction via traditional lectures, while the experimental group was treated using computer animation. The Hybridization Achievement Test (HAT) and Students' Spatial Ability Test (SSAT) were tested and used for data collection. The tests had reliability coefficients of 0.71 and 0.77, respectively using Kuder Richardson 20. Using estimated marginal means and Analysis of Covariance (ANCOVA) at a 0.05 significance level, seven research hypotheses were tested. Results showed that CAI highly impacted students' performance in the chemical concept of hybridization. A noteworthy interaction effect between gender and spatial ability was also found, favouring females with high spatial ability over males with low spatial ability regarding learners' performance. The research results indicate that CAI enhanced students' performance on the hybridization concept in chemistry. The results also showed the gender-friendly and successful instructional characteristics of CAI. [ABSTRACT FROM AUTHOR]

While computer animations have the potential to assist learners in understanding difficult concepts and eliminating misconceptions, studies supporting this claim are scarce. This study investigated how the 7E instructional model integrated with computer animations affected students' conceptual understanding and misconceptions about food making and plant growth. Experimental groups were taught the 7E learning cycle model [7E LCM], and 7E LCM with computer animation [CA] while the control group was taught the conventional instruction method. A two-tiered conceptual understanding multiple-choice test and semi-structured interviews were used to collect the data. ANOVA analysis revealed no significant differences between groups or genders in pre-food making and growth in plant conceptual understanding [pre-FMGPCU] and pre-misconceptions test scores [pre-MC]. There were, however, significant differences in post-FMGPCU and post-MC mean scores, with the 7E LCM with CA showing better results in improving conceptual understanding and minimizing misconceptions. MANOVA revealed no statistically significant difference between male and female students' post-FMGPCU and post-MC results. It was concluded that the 7E LCM with CA enhances students' conceptual understanding and minimizes misconceptions more effectively than other instructional approaches. It is recommended that similar designs be used in biology teaching. [ABSTRACT FROM AUTHOR]

While computer animations have the potential to assist learners in understanding difficult concepts and eliminating misconceptions, studies supporting this claim are scarce. This study investigated how the 7E instructional model integrated with computer animations affected students' conceptual understanding and misconceptions about food making and plant growth. Experimental groups were taught the 7E learning cycle model [7E LCM], and 7E LCM with computer animation [CA] while the control group was taught the conventional instruction method. A two-tiered conceptual understanding multiple-choice test and semi-structured interviews were used to collect the data. ANOVA analysis revealed no significant differences between groups or genders in pre-food making and growth in plant conceptual understanding [pre-FMGPCU] and pre-misconceptions test scores [pre-MC]. There were, however, significant differences in post-FMGPCU and post-MC mean scores, with the 7E LCM with CA showing better results in improving conceptual understanding and minimizing misconceptions. MANOVA revealed no statistically significant difference between male and female students' post-FMGPCU and post-MC results. It was concluded that the 7E LCM with CA enhances students' conceptual understanding and minimizes misconceptions more effectively than other instructional approaches. It is recommended that similar designs be used in biology teaching.

Summary: Generating immersive virtual reality avatars is a challenging task in VR/AR applications, which maps physical human body poses to avatars in virtual scenes for an immersive user experience. However, most existing work is time‐consuming and limited by datasets, which does not satisfy immersive and real‐time requirements of VR systems. In this paper, we aim to generate 3D real‐time virtual reality avatars based on a monocular camera to solve these problems. Specifically, we first design a self‐attention distillation network (SADNet) for effective human pose estimation, which is guided by a pre‐trained teacher. Secondly, we propose a lightweight pose mapping method for human avatars that utilizes the camera model to map 2D poses to 3D avatar keypoints, generating real‐time human avatars with pose consistency. Finally, we integrate our framework into a VR system, displaying generated 3D pose‐driven avatars on Helmet‐Mounted Display devices for an immersive user experience. We evaluate SADNet on two publicly available datasets. Experimental results show that SADNet achieves a state‐of‐the‐art trade‐off between speed and accuracy. In addition, we conducted a user experience study on the performance and immersion of virtual reality avatars. Results show that pose‐driven 3D human avatars generated by our method are smooth and attractive. [ABSTRACT FROM AUTHOR]

Paying close attention to facial expressions, gestures, and communication techniques is essential when creating animated physician characters that are realistic and captivating when describing surgical procedures. This paper emphasizes the integration of appropriate emotions, co‐speech gestures when medical experts explain the medical procedure, and designing animated characters. We can achieve healthy doctor‐patient relationships and improvement of patients' understanding by depicting these components truthfully. We suggest two critical approaches to developing virtual medical experts by incorporating these elements. First, doctors can generate the contents of the surgical procedure with a virtual doctor. Second, patients can listen to the surgical procedure described by the virtual doctor and ask if they have any questions. Our system helps patients by considering their psychology and adding medical professionals' opinions. These improvements ensure the animated virtual agent is comforting, reassuring, and emotionally supportive. Through a user study, we evaluated our hypothesis and gained insight into improvements. [ABSTRACT FROM AUTHOR]

Dance Coherent Action Generation is a popular research task in recent years to generate movements and actions for computer-generated characters in a simulated environment. It is sometimes referred to as "Motion Synthesis". Motion synthesis algorithms are used to generate physically believable, visually compelling, and contextually appropriate movement using motion sensors. The Dance Coherent Action Generation Model (DCAM) is a generative framework for producing aesthetically pleasing movements using deep learning from small amounts of data. By learning an internal representation of motion dynamics, DCAM can synthesize long sequences of movements in which coherent patterns can be created through latent space interpolation. This framework provides a mechanism for varying the amplitude of the generated motion, allowing further realistic thinking and expression. The proposed model obtained 93.79% accuracy, 93.79% precision, 97.75% recall and 92.92% F1 score. DCAM exploits the balance between imitation and creativity by enabling the production of novel outputs from limited input data and can be trained in an unsupervised manner or fine-tuned with sparse supervision. Furthermore, the framework is easily extended to handle multiple layers of abstraction and can be further personalized to a particular type of movement, enabling the generation of highly individualized outputs. [ABSTRACT FROM AUTHOR]

Abstract The image‐to‐image translation (I2IT) task aims to transform images from the source domain into the specified target domain. State‐of‐the‐art CycleGAN‐based translation algorithms typically use cycle consistency loss and latent regression loss to constrain translation. In this work, it is demonstrated that the model parameters constrained by the cycle consistency loss and the latent regression loss are equivalent to optimizing the medians of the data distribution and the generative distribution. In addition, there is a style bias in the translation. This bias interacts between the generator and the style encoder and visually exhibits translation errors, e.g. the style of the generated image is not equal to the style of the reference image. To address these issues, a new I2IT model termed high‐quality‐I2IT (HQ‐I2IT) is proposed. The optimization scheme is redesigned to prevent the model from optimizing the median of the data distribution. In addition, by separating the optimization of the generator and the latent code estimator, the redesigned model avoids error interactions and gradually corrects errors during training, thereby avoiding learning the median of the generated distribution. The experimental results demonstrate that the visual quality of the images produced by HQ‐I2IT is significantly improved without changing the generator structure, especially when guided by the reference images. Specifically, the Fréchet inception distance on the AFHQ and CelebA‐HQ datasets are reduced from 19.8 to 10.2 and from 23.8 to 17.0, respectively.

The image‐to‐image translation (I2IT) task aims to transform images from the source domain into the specified target domain. State‐of‐the‐art CycleGAN‐based translation algorithms typically use cycle consistency loss and latent regression loss to constrain translation. In this work, it is demonstrated that the model parameters constrained by the cycle consistency loss and the latent regression loss are equivalent to optimizing the medians of the data distribution and the generative distribution. In addition, there is a style bias in the translation. This bias interacts between the generator and the style encoder and visually exhibits translation errors, e.g. the style of the generated image is not equal to the style of the reference image. To address these issues, a new I2IT model termed high‐quality‐I2IT (HQ‐I2IT) is proposed. The optimization scheme is redesigned to prevent the model from optimizing the median of the data distribution. In addition, by separating the optimization of the generator and the latent code estimator, the redesigned model avoids error interactions and gradually corrects errors during training, thereby avoiding learning the median of the generated distribution. The experimental results demonstrate that the visual quality of the images produced by HQ‐I2IT is significantly improved without changing the generator structure, especially when guided by the reference images. Specifically, the Fréchet inception distance on the AFHQ and CelebA‐HQ datasets are reduced from 19.8 to 10.2 and from 23.8 to 17.0, respectively. [ABSTRACT FROM AUTHOR]

The analysis of movements is one of the notable applications within the field of computer animation. Sophisticated motion capture techniques allow to acquire motion and store it in a digital form for further analysis. The combination of these two aspects of computer vision enables the presentation of data in an accessible way for the user. The primary objective of this study is to introduce an artificial intelligence-based system for animating tennis motion capture data. The Dual Attention Graph Convolutional Network was applied. Its unique approach consists of two attention modules, one for body analysis and the other for tennis racket alignment. The input to the classifier is a sequence of three dimensional data generated from the Mocap system and containing an object of a player holding a tennis racket and presenting fundamental tennis hits, which are classified with great success, reaching a maximum accuracy over 95%. The recognised movements are further processed using dedicated software. Movement sequences are assigned to the tennis player's 3D digital model. In this way, realistic character animations are obtained, reflecting the recognised moves that can be further applied in movies, video games and other visual projects.

The present study shows the development of computational algorithms to represent aircraft instruments such as the attitude indicator or the turn-and-slip indicator; moreover, the algorithms represent a magnetic compass and other instruments that function according to other physical theories. These instruments work by using the gyroscope and magnetic principles and help the pilot in navigation. These are considered to be the basic instruments required to provide location-related and positional information about the actual aircraft attitude. The algorithms developed in this study are capable of working in concordance with other instruments and the physical conditions established. The programming language used was C++ and the algorithms were compiled in independent files and subroutines for computational efficiency, eliminating unnecessary code. The display options were successfully tested. Additionally, an analysis that evaluated the error and approached flight simulation as a function of step time (Δt) is also described.

In terrorist attack simulations, existing methods do not describe individual differences, which means different individuals will not have different behaviors. To address this problem, we propose a framework to model people’s heterogeneous behaviors in terrorist attack. For pedestrian, we construct an emotional model that takes into account its personality and visual perception. The emotional model is then combined with pedestrians' relationship networks to make the decision-making model. With the proposed decision-making model, pedestrian may have altruistic behaviors. For terrorist, a mapping model is developed to map its antisocial personality to its attacking strategy. The experiments show that the proposed algorithm can generate realistic heterogeneous behaviors that are consistent with existing psychological research findings.

Automatic acupoint searching is an indispensable part of intelligent acupuncture robot. Clinical practice have proofed that Dazhu, Fengmen and Xinshu, which could be located by Dazhui, are curative when these points are acupuncture. The existing methods are mainly based on regular or image. The regular‐based methods are based on the experience of physicians, and the accuracy will decrease for different patients; While the image‐based methods will lose some features in image. In order to solve the existing problems, we propose a novel graph convolution mixed with point cloud deep learning method. In this method, the skinned multi‐person linear model is regarded as a graph structure input, and the coarsened graph is obtained by graph convolution. After feeding the coarsened graph into the PointNet network, the coordinates of Dazhui are output. Different from the existing methods, the proposed method can directly label the results on the adaptive model, thus improving the accuracy on different models. An optimization method based on graph structure is introduced for better fit the predicted acupoints to the surface. In addition, a dataset marked with Dazhui is constructed for training. Experiments show that the accuracy of positioning could meet the requirements of needle application under certain circumstances. [ABSTRACT FROM AUTHOR]

This article is devoted to solving the problem of accumulation, systematization, and translation of the practices of using digital educational technologies in municipal educational organizations. The solution to this problem was implemented by implementing the project "Organization of a system of digital education practices in the urban district of the City of Yelets" in 2022. The project was aimed at involving at least 350 managing and teaching staff, 4000 students in the active practice of using digital educational technologies in educational organizations of the urban district of Yelets (Lipetsk region, Russian Federation) by the end of 2022. To achieve the goal, the implementation of a system of digital education practices in educational organizations of the urban district of the city of Yelets was determined. Continuity and concession are key features of this system. Consequently, the stakeholders are preschool educational organizations, public educational organizations, organizations of additional education, secondary vocational education, and higher education. This system involved the use of such organizational forms as a resource center, a municipal network platform, a pivotal school, and an author's school, within which approbation, tuning, and dissemination of the experience of using software products, the LECTA digital educational platform, the digital educational environment "Mobile e-education" and directions 3D modeling, digital video and robotics. The key results of the conducted research were quantitative and qualitative indicators. The main problem that has blocked the adoption of digital education tools among the pedagogical community is the belief that they are ineffective compared to full-time education. [ABSTRACT FROM AUTHOR]

The analysis of movements is one of the notable applications within the field of computer animation. Sophisticated motion capture techniques allow to acquire motion and store it in a digital form for further analysis. The combination of these two aspects of computer vision enables the presentation of data in an accessible way for the user. The primary objective of this study is to introduce an artificial intelligence-based system for animating tennis motion capture data. The Dual Attention Graph Convolutional Network was applied. Its unique approach consists of two attention modules, one for body analysis and the other for tennis racket alignment. The input to the classifier is a sequence of three dimensional data generated from the Mocap system and containing an object of a player holding a tennis racket and presenting fundamental tennis hits, which are classified with great success, reaching a maximum accuracy over 95%. The recognised movements are further processed using dedicated software. Movement sequences are assigned to the tennis player's 3D digital model. In this way, realistic character animations are obtained, reflecting the recognised moves that can be further applied in movies, video games and other visual projects. [ABSTRACT FROM AUTHOR]

Fluid simulation is well‐known for being visually stunning while computationally expensive. Spatial adaptivity can effectively ease the computational cost by discretizing the simulation space with varying resolutions. Adaptive methods nowadays mainly focus on the mechanism of refining the fluid surfaces to obtain more vivid splashes and wave effects. But such techniques hinder further performance gain under the condition where most of the vast fluid surface is tranquil. Moreover, energetic flow beneath the surface cannot be adequately captured with the interior of the fluid still being simulated under coarse discretization. This article proposes a novel boundary‐distance based adaptive method for smoothed particle hydrodynamics fluid simulation. The signed‐distance field constructed with respect to the coupling boundary is introduced to determine particle resolution in different spatial positions. The resolution is maximal within a specific distance to the boundary and decreases smoothly as the distance increases until a threshold is reached. The sizes of the particles are then adjusted towards the resolution via splitting and merging. Additionally, a wake flow preservation mechanism is introduced to keep the particle resolution at a high level for a period of time after a particle flows through the boundary object to prevent the loss of flow details. Experiments show that our method can refine fluid–solid coupling details more efficiently and effectively capture dynamic effects beneath the surface. [ABSTRACT FROM AUTHOR]

This article examines the critical and cultural framing of the Walt Disney Studio's cel- and computer-animated feature films according to an enduring art-historical narrative. It traces the critical evolution and historical periodization of Disney animation from the 1930s and 1940s to the post-millennial period, arguing that the studio has often been understood according to 'early, middle and late' phases of production that are typically held as both complementary and in tension with each other. Supported by the well-established art-history vernacular that has defined discrete Disney eras, this article then argues for post-2012 Disney Feature Animation as an example of the studio's 'late style' – a later phase not of transgression or alienation, but one that adheres to a more positivist mode that signals pleasurable formal dissidence, confident deformation, and artistic creativity. This article subsequently advances the term 'Disney Baroque' to describe such playful transformations of digital aesthetics and effects present across the studio's nine features released between Wreck-It Ralph (Rich Moore, 2012) and Encanto (Jared Bush and Byron Howard, 2021), its longest run of computer-animated films. By sharpening contemporary Disney's connections to the ahistorical or atemporal logic of Baroque theatricality, this article identifies how contemporary Disney animation engineers spectacular moments of upheaval that rest on specific Neo-Baroque qualities (concealment, illusionism, representationalism, polycentricism, seriality, the labyrinthine) in ways that further contribute to an understanding of Disney's own internal history and critical periodicity. [ABSTRACT FROM AUTHOR]

The informal heuristic practices of the fine arts have much to offer to our understanding of the appearance of phenomenological reality. One interesting example is the use of exaggeration to enhance the illusion of liveliness in both living and nonliving subjects. This further eases the uncomfortable sense that the motion is somehow uncanny — especially with inanimate objects. We performed a series of experiments to test the effects of exaggeration on the phenomenological perception of simple animated objects — bouncing balls. A physically plausible model of a bouncing ball was augmented with a frequently used form of exaggeration known as squash and stretch. Observers were shown a series of animated balls, depicted using systematic parameterizations of the exaggeration model, and asked to rate their plausibility. A range of rendering styles provided varying levels of information as to the type of ball. In all cases, balls with small amounts of exaggeration were seen as plausible as those without any exaggeration (e.g., with veridical motion). Furthermore, when the type of ball was not specified, observers tolerated a large amount of exaggeration before judging them as implausible. When the type of ball was indicated, observers narrowed the range of acceptable exaggeration somewhat but still tolerated exaggeration well beyond that which would be physically possible. We contend that, in this case, exaggeration acts to bridge the so-called uncanny valley for artificial depictions of physical reality. [ABSTRACT FROM AUTHOR]

The study was designed to investigate the impact of First Principles of Instruction (FPI) with computer animation and chart, and their functional effect on gender to acquire expertise in science in Junior High School (JHS). The content for the treatments was selected from JHS integrated science syllabus. The contents of the instructional media were designed in line with the specifications of Principles of Multimedia Learning (PML). All the learning tasks for the two treatments were designed based on FPI. Eighty- seven second-year JHS students (male = 48, female = 39) with a mean age of 14.4 years were randomly assigned to the two treatments. Ateacher was trained to deliver the content. The main study consisted of three sessions, which were delivered in the regular classroom and computer laboratory. Paired-sample and independent t-tests and univariate analyses were used to analyze the data. The result showed that there was no statistically significant difference between the two treatments. In addition, the result revealed no significant interaction effect on gender and the two treatments for the acquisition of expertise in science at the basic school. The findings are novel and suggest that static/inexpensive instructional media (e.g.chart) carefully designed with specifications of PML integrated withFPI is equally effective as dynamic instructional media (e.g., computer animation) for the development of expertise in science in the context of traditional classrooms of basic schools irrespective of the gender of the students.