Graphical Tasks Research Articles

Mathematical discussion in classrooms as a technologically-supported activity fostering participation and inclusion

AbstractWhole-class mathematical discussion in a problem-solving activity is recognized as a powerful pedagogical activity but also a challenge for teachers who must consider several difficulties that learners might face, particularly in terms of an overload of Working Memory and Executive Functions. This study investigates how the use of a digital platform (Padlet) can support participatory and inclusive mathematical classroom discussion. We proposed a teaching experiment based on graphical tasks anticipating integral calculus to grade 13 students, and we examined how the use of the digital platform plays a role in the construction and interpretation of new mathematical objects emerging from the activity. The use of Instrumental Genesis and Double Instrumental Genesis frameworks allowed us to make the affordances of the tool emerge. As a result, we got evidence of how mathematical discussion may develop as a network of interactions, feedback, and connection of input and discuss examples of how active participation and inclusion are enhanced by the tool affordances. Indeed, the digital platform allowed easy interaction, with many ways to represent and express the ongoing evolution of personal and shared meanings and the possibility to manage the time of the activity. This fostered students’ participation and students which did not participate in previous discussions were actively engaged in it.

Using Multi-Level Consistency Learning for Partial-to-Partial Point Cloud Registration.

Point cloud registration is a basic task in computer vision and computer graphics. Recently, deep learning-based end-to-end methods have made great progress in this field. One of the challenges of these methods is to deal with partial-to-partial registration tasks. In this work, we propose a novel end-to-end framework called MCLNet that makes full use of multi-level consistency for point cloud registration. First, the point-level consistency is exploited to prune points located outside overlapping regions. Second, we propose a multi-scale attention module to perform consistency learning at the correspondence-level for obtaining reliable correspondences. To further improve the accuracy of our method, we propose a novel scheme to estimate the transformation based on geometric consistency between correspondences. Compared to baseline methods, experimental results show that our method performs well on smaller-scale data, especially with exact matches. The reference time and memory footprint of our method are relatively balanced, which is more beneficial for practical applications.

Формування графічної компетентності майбутніх фахівців технічних спеціальностей засобами штучного інтелекту

The article considers the use of artificial intelligence tools to improve the efficiency of teaching graphic disciplines. The article analyses the possibilities of AI for personalising the learning process, automated assessment, providing interactive tasks and real-time feedback. Such approaches can increase student motivation, improve the quality of learning outcomes, and make the learning process more adaptive to the individual needs of each student. Special attention is paid to the impact of AI on the development of professional skills of students of technical specialities. The use of interactive simulations and virtual environments controlled by artificial intelligence helps students to better master complex graphic and spatial concepts. Students have the opportunity to independently work on graphic tasks in a virtual environment that simulates real-world professional conditions, while receiving instant feedback from the system. This approach also promotes critical thinking and creativity in solving graphic problems. The article also discusses methodological approaches to the introduction of AI into curricula, in particular, the integration of new technologies into the educational process without disrupting traditional educational methods. It is noted that effective integration of AI requires an integrated approach, where technologies work in cooperation with the teacher, complementing traditional teaching methods and creating conditions for the development of the necessary competencies in students. The importance of an integrated approach to the use of artificial intelligence, where technologies complement traditional teaching methods, contributing to the development of graphic competence, is substantiated. Future research will be aimed at an in-depth study of ways to improve the teaching of graphic disciplines using artificial intelligence, as well as their integration into programmes for students with special educational needs.

Understanding the differences in the use of graphic tool and planning during graphic execution between individuals with autism and typically developing individuals

Individuals with autism (ASD) often face difficulty in executing graphic tasks. This can be related to how one uses a graphic tool (e.g., pen) and plans ahead the graphic execution. Use of graphic tool can be captured using attributes, e.g., pen-tip pressure, number of pen lifts, etc. One’s ability to plan a graphic execution can be quantified using the total duration of pen lifts (i.e., air time). Though pen-and-paper-based Trail Making Test-Part A (TMT-A) can estimate planning of graphic execution, yet it cannot capture other attributes, e.g., pen-tip pressure, pen lift, etc. This can be possible if TMT-A is administered on a pressure-sensitive tablet as seen from existing studies with typically developing (TD) individuals. However, quantification of such attributes using TMT-A administered on a pressure-sensitive tablet remains unexplored for individuals with ASD. In addition, such objective measures can help to understand variations in the use of graphic tool and ability to plan graphic execution even outside the TMT-A task, e.g., while drawing shapes which is important to the development of children’s graphic skills. Here, we conducted a study with 12 pairs of TD children and those with ASD who executed TMT-A (in Phase-I) and shape drawing (in Phase-II) on a pressure-sensitive tablet. Results of our study show differences in the use of graphic tool and planning ahead the graphic execution between two participant groups in both the Phases. Such insights can offer clinical inputs that can be helpful in designing individualized intervention paradigms for children facing difficulties in graphic execution.

SGRTmreg: A Learning-Based Optimization Framework for Multiple Pairwise Registrations.

Point cloud registration is a fundamental task in computer vision and graphics, which is widely used in 3D reconstruction, object tracking, and atlas reconstruction. Learning-based optimization and deep learning methods have been widely developed in pairwise registration due to their own distinctive advantages. Deep learning methods offer greater flexibility and enable registering unseen point clouds that are not trained. Learning-based optimization methods exhibit enhanced robustness and stability when handling registration under various perturbations, such as noise, outliers, and occlusions. To leverage the strengths of both approaches to achieve a less time-consuming, robust, and stable registration for multiple instances, we propose a novel computational framework called SGRTmreg for multiple pairwise registrations in this paper. The SGRTmreg framework utilizes three components-a Searching scheme, a learning-based optimization method called Graph-based Reweighted discriminative optimization (GRDO), and a Transfer module to achieve multi-instance point cloud registration.Given a collection of instances to be matched, a template as a target point cloud, and an instance as a source point cloud, the searching scheme selects one point cloud from the collection that closely resembles the source. GRDO then learns a sequence of regressors by aligning the source to the target, while the transfer module stores and applies the learned regressors to align the selected point cloud to the target and estimate the transformation of the selected point cloud. In short, SGRTmreg harnesses a shared sequence of regressors to register multiple point clouds to a target point cloud. We conduct extensive registration experiments on various datasets to evaluate the proposed framework. The experimental results demonstrate that SGRTmreg achieves multiple pairwise registrations with higher accuracy, robustness, and stability than the state-of-the-art deep learning and traditional registration methods.

Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation

Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full-head generation methods require a large number of three-dimensional (3D) scans or multi-view images to train the model, resulting in expensive data acquisition costs. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver the 3D frontal faces within complete heads without compromising head integrity. To mitigate the domain gap between the face and head models, we present a dual-discriminator to guide the frontal and back head generation. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations. Extensive experiments demonstrate the effectiveness of our proposed Head3D, both qualitatively and quantitatively.

Exploring Challenges Faced by Engineering Students in Graphic Preparations of Perspective Geometry

Perspective geometry is a fundamental, challenging, and captivating subject within the engineering bachelor's degree program. It holds significant importance in developing graphic skills, analytical abilities, sketching proficiency, and comprehension of drawings. Moreover, it plays a crucial role in organizing the architectural components of a bachelor's thesis. However, the teaching and learning of perspective geometry often reveal various difficulties and shortcomings. Moreover, one of the various systems of symbols and languages created by global cultures is the graphical language, which is an exceptional and unparalleled language for understanding scientific and technical information. This language is considered the oldest international language. Every visual piece of information in various processes of human life has been formed through the graphical language, which is composed of various geometric shapes. In this research, data has been gathered from the perspectives of first-year students from the 2013 batch regarding the difficulties encountered in perspective geometry. A questionnaire was distributed to collect their opinions, and three graphical tasks with different levels of complexity were given to the students. The results obtained from this study indicate that employing suitable teaching methods and providing adequate resources can alleviate most of the learning difficulties associated with graphic skills. Instructors also play a pivotal role in resolving learning obstacles. Therefore, efforts should be made to enhance the quality of teaching graphic subjects by updating the content and curriculum of educational programs and improving teaching methods through the use of technology. In higher education institutions, conditions for fostering students' professional knowledge, enhancing their ability to draw maps and create technical documents can be facilitated through computer graphics education. Updating the teaching methods plays a crucial role in improving the quality of graphic education. The mentioned factors provide a suitable environment for the growth of graphic knowledge and the implementation of projects related to professional subjects.

THE INFLUENCE OF GRAPHIC TRAINING ON THE FORMATION OF INFORMATION AND COMMUNICATION COMPETENCE OF FUTURE TECHNOLOGY TEACHERS

The article carefully examines the influence of graphic training on the formation of information and communication competence of future technology teachers. The key aspects of the need to integrate information and communication technologies into the educational process of graphic disciplines are analyzed, pointing out the limits of traditional teaching methods in the context of a dynamically developing information society. It is emphasized that the content of graphic disciplines must have an applied, professionally oriented character, which requires educational programs to take into account the specifics of the graphic activity of a modern technology teacher and involves the application of a complex of knowledge and skills to solve engineering and graphic tasks. The influence of the use of information technologies on the learning process is discussed in detail, which contributes not only to the optimization of the knowledge acquisition process, but also to the development of critical thinking, student independence and their ability to analyze and forecast. It is highlighted that computer technologies, as a modern tool of didactics, significantly expand the possibilities of visualizing educational material, which has a significant impact on the formation of basic graphic competencies. The research defines the prospects for further scientific work, which include the development of a theoretical and methodological basis for graphic training in the conditions of the information society, the creation of educational and methodological support that meets modern requirements, the formation of an information and communication educational space, as well as the development of effective control and diagnostic tools. This approach will ensure deep and comprehensive assimilation by future technology teachers of the necessary knowledge and skills that meet the requirements of modern education and the labor market, contributing to the formation of highly qualified specialists capable of effective use of innovative technologies in their professional activities.

Local geometry-perceptive mesh convolution with multi-ring receptive field

Learning 3D mesh representation is necessary for many computer vision and graphic tasks. Recently, some works have studied convolution methods for directly processing input meshes. However, these methods are usually weak in extracting local geometry information because of the disadvantages such as isotropic filter, neglect of mesh topology, and a small convolution field. In this paper, we introduce a local geometry-perceptive mesh convolution, which pays attention to mesh irregular structures for efficiently capturing geometry features in a multi-ring receptive field. Specifically, we define each template node’s dynamic neighbor-attention weights used in multiple attention aggregation operations for obtaining local mesh change information of different vertices in the multi-ring field. After each aggregation, a shared anisotropic filter maps the catenation of each new vertex and its neighbors for extracting geometry features of the current ring. Then, complete local geometry features of each vertex in its large local field are obtained by summing the mapped results of each aggregation. Moreover, the position features of each vertex are added to its local geometry features to get the final representation vector of the vertex. We demonstrate the proposed mesh convolution method’s strong ability in modeling 3D mesh shapes.

Transformer for Image Harmonization and Beyond.

Image harmonization, aiming to make composite images look more realistic, is an important and challenging task. The composite, synthesized by combining foreground from one image with background from another image, inevitably suffers from the issue of inharmonious appearance caused by distinct imaging conditions, i.e., lights. Current solutions mainly adopt an encoder-decoder architecture with convolutional neural network (CNN) to capture the context of composite images, trying to understand what it should look like in the foreground referring to surrounding background. In this work, we seek to solve image harmonization with Transformer, by leveraging its powerful ability of modeling long-range context dependencies, for adjusting foreground light to make it compatible with background light while keeping structure and semantics unchanged. We present the design of our two vision Transformer frameworks and corresponding methods, as well as comprehensive experiments and empirical study, demonstrating the power of Transformer and investigating the Transformer for vision. Our methods achieve state-of-the-art performance on the image harmonization as well as four additional vision and graphics tasks, i.e., image enhancement, image inpainting, white-balance editing, and portrait relighting, indicating the superiority of our work. Codes, models, more results and details can be found at the project website http://ouc.ai/project/HarmonyTransformer.

Research on 3D scene graph rendering based on neural radiance fields

Since the release of Neural Radiance Fields (NeRF), it has become the research focus of computer graphics in only three years and has become a representative method of using deep learning to deal with computer graphics tasks. The application scenarios of NeRF are very extensive, including virtual reality, augmented reality, computer graphics, 3D scene graph rendering, and other fields. However, the literatures on these aspects are not sufficient. To this end, this article introduces the basic principles of NeRF and compares and analyzes the advantages and disadvantages of NeRF and traditional graphics methods in 3D rendering tasks. According to different improvement directions, from the perspective of improving training speed, improving network generalization, and expanding to dynamic scenes, etc. Representative follow-up work based on NeRF is summarized. And the future application scenarios and development direction of NeRF are prospected.

Jrender: An efficient differentiable rendering library based on Jittor

Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance.

Lightweight Curvature Estimation on Point Clouds with Randomized Corrected Curvature Measures

AbstractThe estimation of differential quantities on oriented point cloud is a classical step for many geometry processing tasks in computer graphics and vision. Even if many solutions exist to estimate such quantities, they usually fail at satisfying both a stable estimation with theoretical guarantee, and the efficiency of the associated algorithm. Relying on the notion of corrected curvature measures [LRT22, LRTC20] designed for surfaces, the method introduced in this paper meets both requirements. Given a point of interest and a few nearest neighbours, our method estimates the whole curvature tensor information by generating random triangles within these neighbours and normalising the corrected curvature measures by the corrected area measure. We provide a stability theorem showing that our pointwise curvatures are accurate and convergent, provided the noise in position and normal information has a variance smaller than the radius of neighbourhood. Experiments and comparisons with the state‐of‐the‐art confirm that our approach is more accurate and much faster than alternatives. The method is fully parallelizable, requires only one nearest neighbour request per point of computation, and is trivial to implement.

C2SPoint: A classification-to-saliency network for point cloud saliency detection

Point cloud saliency detection is an important technique that support downstream tasks in 3D graphics and vision, like 3D model simplification, compression, reconstruction and viewpoint selection. Existing approaches often rely on hand-crafted features and are only applicable to specific datasets. In this paper, we propose a novel weakly supervised classification network, called C2SPoint, which directly performs saliency detection on the point clouds. Unlike previous methods that require per-point saliency annotations, C2SPoint only requires category labels of the point clouds during training. The network consists of two branches: a Classification branch and a Saliency branch. The former branch is composed of two Adaptive Set Abstraction layers for feature extraction and a Saliency Transform layer for learning saliency knowledge from the classification network. The latter branch introduces a multi-scale point-cluster similarity matrix for propagating the cluster saliency to each point within it, resulting in the prediction of point-level saliency. Experimental results demonstrate the effectiveness of our method in point cloud saliency detection, with improvements of 2% in both AUC and NSS compared to state-of-the-art methods.

A truncated generalized Huber prior for image smoothing

Image smoothing is a fundamental task in computer vision and graphics. This paper presents a new image smoothing method based on a truncated generalized Huber prior. The proposed model is neither convex nor concave and is hard to optimize. We first transform the prior into a concave one, then utilize the technique of half-quadratic minimization to get an equivalent convex surrogate function. Thus the numerical algorithm is obtained by solving a weighted least square problem and iteratively updating the weights. The convergence of the algorithm is theoretically guaranteed. The proposed method is flexible and powerful in preserving edge/structure and eliminating undesired information. The effectiveness of the proposed method is demonstrated by several applications, including scale space filtering, texture removal, and clip-art JPEG artifacts removal.

Meshless power diagrams

The computation of power diagrams (or weighted Voronoi diagrams) is a fundamental task in computational geometry and computer graphics. To accomplish the computation, we provide a different way from the existing ones for lifting the weighted seeds to a set of points in the space of one dimension higher, then the power cells can be directly obtained by computing the intersections of the Voronoi cells of these lifting points and the original space. This property enables us to apply the method based on the k-nearest neighbors query to the generation of power diagrams. Each power cell is obtained by sequentially clipping the input domain using the bisectors between its seed and the k-nearest neighbors. Experimental results demonstrate that our method outperforms the state-of-the-art one based on regular triangulation in terms of efficiency for general cases in the 2D and 3D spaces.

Enabling End-Users in Designing and Executing of Complex, Collaborative Robotic Processes

Over the last years, capabilities of robotic systems have quantitatively and qualitatively improved. But going beyond isolated robotic systems, the integration and interoperability of robotic capabilities in complex work processes remains a major challenge. This lack of tools to integrate robots needs to be addressed on technical, semantic and organizational level. In the ROBxTASK research project, we developed an approach to support cooperation between different types of users in order to enable domain experts, with no robotic know-how, to work with robot-assisted workflows. By engineering robotic skills at a useful and usable level of abstraction for experts in different domains, we aim to increase re-usability of these skills on two different levels, (robotic) device level, and on level of application specific workflows. The researched prototype consists of a web platform, which allows (a) engineers to register (robotic) devices and the implemented skills of the devices, (b) domain experts to use a graphical task design environment to create workflows across multiple robotic devices and lastly (c) robot co-workers to download and execute the workflow code in a local environment with digital twins or real robots. Additionally skills and workflows can be shared across organisations. Initial user studies have shown that the visual programming environment is accessible and the defined skill-set is easy to understand even for domain experts that are inexperienced in the field of robotics.

РАЗВИТИЕ ТВОРЧЕСКОГО МЫШЛЕНИЯ ЛИЧНОСТИ В ПРОЦЕССЕ ОБУЧЕНИЯ ИНЖЕНЕРНОЙ ГРАФИКЕ

The article deals with the development and formation of creative thinking of the individual in the process of teaching Engineering graphics, as well as the structure of classes aimed at developing the creativity of students. The proposed examples of graphic tasks in Engineering Graphics contain a problem, reveal new aspects of the object under study based on the analysis of the initial data, and bring students as close as possible to their professional activities.

ПРОБЛЕМЫ ГЕОМЕТРО-ГРАФИЧЕСКОЙ ПОДГОТОВКИ СТУДЕНТОВ ВУЗОВ

It is noted that geometric and graphical disciplines traditionally cause difficulties in studying elementary students. It is pointed out that the requirements for the quality of education and ensuring academic performance are mutually inverse and are in conflict with the limited number of teaching hours, which has been steadily declining for many years. Data are given on the number of hours allocated for the study of geometric and graphic disciplines in Russian universities. The main reasons for the problems of geometric and graphic training of students are listed. The first reason is an attempt to give knowledge and skills from three different sections - mathematics (descriptive geometry), computer science (computer graphics) and engineering (engineering graphics) in conditions of shortage of classroom hours. Provides information about the content of classical textbooks of descriptive geometry, engineering graphics. The second reason is the complexity of the development of spatial thinking. It is noted that information technologies that facilitate the understanding of images do not solve the problem of the development of spatial thinking. Information is given on the heterogeneity of students in terms of the psychophysiological features of spatial thinking in general and in terms of various types of mathematical thinking. The third reason is the poor initial preparation of students. Features and reasons are indicated. The main ways of increasing the motivation of students to study geometric and graphic disciplines are given. The fourth reason is the unpreparedness of students for independent work. Reasons are given. The main ways of increasing the efficiency of students' independent work are given. The shortcomings of automatic control in the form of testing and automatic verification of solutions of graphic tasks are considered in detail. The fifth reason is the difference in the requirements for geometric and graphic training for different educational areas, specialties and profiles. The presence in the geometric-graphical cycle of disciplines of an invariant (common for different specialties and training profiles) core and subject settings is noted. The sixth reason is the high requirements for lecturers of geometric and graphic disciplines. The problem of training lecturing staff of higher education in the field of geometric and graphic education is noted. Conclusions are made about the need to create a methodological training system that takes into account and solves these problems.

A study of auxiliary screening for Alzheimer's disease based on handwriting characteristics.

Alzheimer's disease (AD) has an insidious onset, the early stages are easily overlooked, and there are no reliable, rapid, and inexpensive ancillary detection methods. This study analyzes the differences in handwriting kinematic characteristics between AD patients and normal elderly people to model handwriting characteristics. The aim is to investigate whether handwriting analysis has a promising future in AD auxiliary screening or even auxiliary diagnosis and to provide a basis for developing a handwriting-based diagnostic tool. Thirty-four AD patients (15 males, 77.15 ± 1.796 years) and 45 healthy controls (20 males, 74.78 ± 2.193 years) were recruited. Participants performed four writing tasks with digital dot-matrix pens which simultaneously captured their handwriting as they wrote. The writing tasks consisted of two graphics tasks and two textual tasks. The two graphics tasks are connecting fixed dots (task 1) and copying intersecting pentagons (task 2), and the two textual tasks are dictating three words (task 3) and copying a sentence (task 4). The data were analyzed by using Student's t-test and Mann-Whitney U test to obtain statistically significant handwriting characteristics. Moreover, seven classification algorithms, such as eXtreme Gradient Boosting (XGB) and Logistic Regression (LR) were used to build classification models. Finally, the Receiver Operating Characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and Area Under Curve (AUC) were used to assess whether writing scores and kinematics parameters are diagnostic. Kinematic analysis showed statistically significant differences between the AD and controlled groups for most parameters (p < 0.05, p < 0.01). The results found that patients with AD showed slower writing speed, tremendous writing pressure, and poorer writing stability. We built statistically significant features into a classification model, among which the model built by XGB was the most effective with a maximum accuracy of 96.55%. The handwriting characteristics also achieved good diagnostic value in the ROC analysis. Task 2 had a better classification effect than task 1. ROC curve analysis showed that the best threshold value was 0.084, accuracy = 96.30%, sensitivity = 100%, specificity = 93.41%, PPV = 92.21%, NPV = 100%, and AUC = 0.991. Task 4 had a better classification effect than task 3. ROC curve analysis showed that the best threshold value was 0.597, accuracy = 96.55%, sensitivity = 94.20%, specificity = 98.37%, PPV = 97.81%, NPV = 95.63%, and AUC = 0.994. This study's results prove that handwriting characteristic analysis is promising in auxiliary AD screening or AD diagnosis.