Traditional Graphics Research Articles

Simulation of Automatically Annotated Visible and Multi-/Hyperspectral Images Using the Helios 3D Plant and Radiative Transfer Modeling Framework.

Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.

EXECUTION OF GRAPHIC STILL-LIFE WITH INK AS THE BASIS FOR MASTERING THE LANGUAGE OF GRAPHICS

The article represents detailed stages and results of performing graphic still-lifes with ink in three main techniques: "lines", "spots", "hatches". Examples and types for setting still-life or alternative using photo images taken from open sources with mandatory changes and introduced details are given. Also the principles and examples for performing graphic and tonal sketches are presented, as an important stage in the search for a composition, which are reproduced on formats of graphic still-lifes through their spot solution to be the most objective and expressive. The technique for making a "cardboard" – a preparatory drawing and transferring the image to the formats of three graphic still-lifes is presented. The usage of tonal graphic sketches and "cardboard" is suggested along with traditional manual techniques and computer (digital) graphics technology. The principles and methods for using lines when creating a graphic still-life in the appropriate technique and variants of performing graphic still-lifes in the techniques of "lines", "spots" in comparison with each other are presented. The principles of division and combination of white and black with variants of their combinatorics are considered on the examples of graphic still-lifes in the "spot" technique. The stages for performing graphic still-lifes in the "hatching" technique, from the disclosure of large tonal gradations to the generalization of the work, are considered in detail. The methods for using different hatching techniques on different parts of the image of a graphic still-life are given. By the separate block for each section of the specified three graphic techniques the parallel between graphic still-lifes as educational tasks and graphic works of professional artists of Ukraine and the world is demonstrated.

Relightable Detailed Human Reconstruction from Sparse Flashlight Images.

We present a lightweight system for reconstructing human geometry and appearance from sparse flashlight images. Our system produces detailed geometry including garment wrinkles and surface reflectance, which are exportable for direct rendering and relighting in traditional graphics pipelines. By capturing multi-view flashlight images using a consumer camera equipped with an co-located LED (e.g., a cell phone), we obtain view-specific shading cues that aid in the determination of surface orientation and help disambiguate between shading and material. To enable the reconstruction of geometry and appearance from sparse-view flashlight images, we integrate a pre-trained model into a differentiable physics-based rendering framework. As the learned image features from synthetic data cannot accurately reflect the shading features on real images, which is crucial for the high-quality reconstruction of geometry details and appearance, we propose to jointly optimize the image feature extractor with two MLPs for SDF and BRDF prediction using the differentiable physics-based rendering. Compared with existing methods for relightable human reconstruction, our system is able to produce high-fidelity 3D human models with more accurate geometry and appearance under the same condition. Our code and data are available at http://github.com/Jarvisss/Relightable_human_recon.

Research on Clothing Art Innovation by Integrating Traditional Graphics and Intelligent Design in the Age of Intelligence

Abstract With the progress of the times, the aesthetics of the public have gradually become diversified, and clothing art design should also keep pace with the times, and carry out the innovation of clothing art design under the integration of traditional graphics. In this paper, the RGB and HSV values of traditional graphics are extracted by the method of color feature extraction, and each pixel is detected by scanning pixel by pixel, and the color characteristics of the graphics are judged according to the pixel points. The roughness and sharpness of the graphic texture are characterized by the gray symbiotic texture features. Combined with the central moments reflecting the distribution of gray levels in the object area relative to the gray level center of gravity metric, the size, shape, and other details of the image are described with the help of higher-order moments of more than three orders. The main direction of clothing art design innovation is analyzed by integrating different features of traditional images into clothing pattern design. The results show that the RGB values in the color design of sweet style clothing should be similar to (255,192,203), (135,206,250), (0,51,0), the entropy value of the graphic texture in the design of clothing art should be >1, and the degree of regularity should be >0.9, so that the regularity and regularity of the graphic is reflected as much as possible. The shape characterization value Φ6 and Φ7 of the image in clothing art design should be 0 to prevent the deformation caused by image scaling and rotation.

FLARE: Fast Learning of Animatable and Relightable Mesh Avatars

Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. While 3D meshes enable efficient processing and are highly portable, they lack realism in terms of shape and appearance. Neural representations, on the other hand, are realistic but lack compatibility and are slow to train and render. Our key insight is that it is possible to efficiently learn high-fidelity 3D mesh representations via differentiable rendering by exploiting highly-optimized methods from traditional computer graphics and approximating some of the components with neural networks. To that end, we introduce FLARE, a technique that enables the creation of animatable and relightable mesh avatars from a single monocular video. First, we learn a canonical geometry using a mesh representation, enabling efficient differentiable rasterization and straightforward animation via learned blendshapes and linear blend skinning weights. Second, we follow physically-based rendering and factor observed colors into intrinsic albedo, roughness, and a neural representation of the illumination, allowing the learned avatars to be relit in novel scenes. Since our input videos are captured on a single device with a narrow field of view, modeling the surrounding environment light is non-trivial. Based on the split-sum approximation for modeling specular reflections, we address this by approximating the prefiltered environment map with a multi-layer perceptron (MLP) modulated by the surface roughness, eliminating the need to explicitly model the light. We demonstrate that our mesh-based avatar formulation, combined with learned deformation, material, and lighting MLPs, produces avatars with high-quality geometry and appearance, while also being efficient to train and render compared to existing approaches.

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.

UDock2: interactive real-time multi-body protein-protein docking software.

Protein-protein docking aims at predicting the geometry of protein interactions to gain insights into the mechanisms underlying these processes and develop new strategies for drug discovery. Interactive and user-oriented manipulation tools can support this task complementary to automated software. This article presents an interactive multi-body protein-protein docking software, UDock2, designed for research but also usable for teaching and popularization of science purposes due to its high usability. In UDock2, the users tackle the conformational space of protein interfaces using an intuitive real-time docking procedure with on-the-fly scoring. UDock2 integrates traditional computer graphics methods to facilitate the visualization and to provide better insight into protein surfaces, interfaces, and properties. UDock2 is open-source, cross-platform (Windows and Linux), and available at http://udock.fr. The code can be accessed at https://gitlab.com/Udock/Udock2.

A Novel Approach to Line Clipping Against a Rectangular Window

Abstract Line clipping against a rectangular window is a fundamental problem in computer graphics. A robust and fast algorithm is needed not only for the traditional graphics pipeline but also for new applications, including web maps, nanomaterials, and sensor measurements. In this paper, we present a novel approach, which is based on the idea of combining the geometric and algebraic approaches. In particular, the proposed approach first decomposes a 2D line clipping problem into a set of 1D clipping problems, and then solves the 1D clipping problem by the comparison (i.e., >, <, and =) operation on the coordinate value of the projected points on one dimension only. Both theoretical analysis and experimental tests were conducted to demonstrate the improved robustness (for degenerated cases) and computational efficiency of the proposed approach.

Calibration of head mounted displays for vision research with virtual reality.

Immersion in virtual environments is an important analog for scientists. Situations that cannot be safely organized in the real world are being simulated virtually to observe, evaluate, and train aspects of human behavior for psychology, therapy, and assessment. However, creating an immersive environment using traditional graphics practices may create conflict with a researcher's goal of evaluating user response to well-defined visual stimuli. Standard computer monitors may display color-accurate stimuli, but it is generally viewed from a seating position, where the participant can see real-world visual context. In this article, we propose a novel means to allow vision scientists to exert finer control over the participants visual stimuli and context. We propose and verify a device-agnostic approach to color calibration by analyzing display properties such as luminance, spectral distribution, and chromaticity. We evaluated five different head-mounted displays from different manufacturers and showed how our approach produces conforming visual outputs.

The Adaptive Streaming SAR Back-Projection Algorithm Based on Half-Precision in GPU

The back-projection (BP) algorithm is completely accurate in the imaging principle, but the computational complexity is extremely high. The single-precision arithmetic used in the traditional graphics processing unit (GPU) acceleration scheme has low throughput and its usage of the video memory is large. An adaptive asynchronous streaming scheme for the BP algorithm based on half-precision is proposed in this study, and then it is extended to the fast back-projection (FBP) algorithm. In this scheme, the adaptive loss factors selection strategy ensures the dynamic range of data, the asynchronous streaming structure ensures the efficiency of large scene imaging, and the mixed-precision data processing ensures the imaging quality. The schemes proposed in this paper are compared with BP, FBP, and fast factorized back-projection (FFBP) algorithms of single-precision in GPU. The experimental results show that the two half-precision acceleration schemes in this paper reduce the video memory usage to 74% and 59% of the single-precision schemes with guaranteed image quality. The efficiency improvements of the proposed schemes are almost one and 0.5 times greater than that of the corresponding single-precision scheme, and the advantage can be more obvious when dealing with large computations.

Multiple HD Screen-Based Virtual Studio System with Learned Mask-Free Portrait Harmonization

Virtual studio technology allows producers to combine live-action footage and computer-generated imagery and has promoted the development of film and television industry. However, the existing green screen-based virtual studio limits the visual effects just in postproduction. In this paper, we propose a new virtual studio system based on the recent emerging technology using multiple high-definition (HD) screens. Besides using traditional computer graphics like other similar systems, our system enables to capture panoramic video from the real world as the background and project it onto multiple HD screens, so as to recreate the scene in the studio. In addition, we propose a mask-free portrait harmonization network to make sure that the appearances of the foreground region and the background are consistent. Our portrait harmonization network does not need any auxiliary foreground mask and works in an end-to-end manner, which meets the postprocessing requirements for our virtual studio. Experimental result on real composite images shows that our network is superior to the state-of-the-art image harmonization method under the task of portrait harmonization. We also demonstrate our system with a CAVE system.

Design on Intelligent Feature Graphics Based on Convolution Operation

With the development and application of artificial intelligence, the technical methods of intelligent image processing and graphic design need to be explored to realize the intelligent graphic design based on traditional graphics such as pottery engraving graphics. An optimized method is aimed to be explored to extract the image features from traditional engraving graphics on historical relics and apply them into intelligent graphic design. For this purpose, an image feature extracted model based on convolution operation is proposed. Parametric test and effectiveness research are conducted to evaluate the performance of the proposed model. Theoretical and practical research shows that the image-extracted model has a significant effect on the extraction of image features from traditional engraving graphics because the image brightness processing greatly simplifies the process of image feature extraction, and the convolution operation improves the accuracy. Based on the brightness feature map output from the proposed model, the design algorithm of intelligent feature graphic is presented to create the feature graphics, which can be directly applied to design the intelligent graphical interface. Taking some pottery engraving graphics from the Neolithic Age as an example, we conduct the practice on image feature extraction and feature graphic design, the results of which further verify the effectiveness of the proposed method. This paper provides a theoretical basis for the application of traditional engraving graphics in intelligent graphical interface design for AI products such as smart tourism products, smart museums, and so on.

КОМПЬЮТЕРНАЯ ГРАФИКА КАК ВИД КОМПЬЮТЕРНОГО ИЗОБРАЗИТЕЛЬНОГО ИСКУССТВА

The article is devoted to computer graphics as the main type of computer visual art. It gives a historical review of the origin of computer graphics. The first artists in computer graphics are: Ben Laposki, Herbert Franke, Michael Noll, Friederich Nake, Charles Xuri, Harold Cohen. The concepts of pencil, charcoal, computer graphics, computer art, engraving, etching, linocut are covered. A comparative analysis of traditional graphic art and computer graphics is conducted. The article provides a brief historical overview of graphite, Italian and lead pencils and focuses on the imitation of traditional graphic tools in graphic editors. It is emphasized that hatchings modelling plays a special role in imitation of pencil drawing technique by means of computer graphics, as well as in traditional drawing. The shading modelling methods developed by software artists Cortez, Yamamoto, Herzmann, Litvinovich, Shiraishi, and Yamaguchi are described. The popularity of engravings in illustrating books and periodicals is noted. A classification of printed graphics by type and production technique is carried out. The article provides an overview of the main imitation filters for all types of engraving. In particular, such filters as "Engraver", "Cutline" Linocut are considered.

In-Memory Realization of Eligibility Traces Based on Conductance Drift of Phase Change Memory for Energy-Efficient Reinforcement Learning.

Reinforcement learning (RL) has shown outstanding performance in handling complex tasks in recent years. Eligibility trace (ET), a fundamental and important mechanism in reinforcement learning, records critical states with attenuation and guides the update of policy, which plays a crucial role in accelerating the convergence of RL training. However, ET implementation on conventional digital computing hardware is energy hungry and restricted by the memory wall due to massive calculation of exponential decay functions. Here, in-memory realization of ET for energy-efficient reinforcement learning with outstanding performance in discrete- and continuous-state RL tasks is demonstrated. For the first time, the inherent conductance drift of phase change memory is exploited as physical decay function to realize in-memory eligibility trace, demonstrating excellent performance during RL training in various tasks. The spontaneous in-memory decay computing and storage of policy in the same phase change memory give rise to significantly enhanced energy efficiency compared with traditional graphics processing unit platforms. This work therefore provides a holistic energy and hardware efficient method for both training and inference of reinforcement learning.

St. Paul's outside the Walls: A Roman Basilica, from Antiquity to the Modern Era

St. Paul's outside the Walls: A Roman Basilica, from Antiquity to the Modern Era

Application of 3D Modeling Technology in Engineering Graphics

With the development of technology and the progress of the times, the application methods and expression methods (including teaching methods) of engineering drawings have undergone tremendous changes. This article analyzes the reasons that restrict the three-dimensional design method can not completely replace the two-dimensional drawing in the short term, and proposes the teaching reform direction that combines the three-dimensional modeling with the traditional graphics content. It clarifies the role of 3D modeling content in graphics courses at this stage, and explains the specific methods of introducing 3D modeling in different stages of graphics courses and the choice of teaching software.

Graph-Guided Deformation for Point Cloud Completion

For a long time, the point cloud completion task has been regarded as a pure generation task. After obtaining the global shape code through the encoder, a complete point cloud is generated using the shape priorly learnt by the networks. However, such models are undesirably biased towards prior average objects and inherently limited to fit geometry details. In this letter, we propose a Graph-Guided Deformation Network, which respectively regards the input data and intermediate generation as controlling and supporting points, and models the optimization guided by a graph convolutional network(GCN) for the point cloud completion task. Our key insight is to simulate the least square Laplacian deformation process via mesh deformation methods, which brings adaptivity for modeling variation in geometry details. By this means, we also reduce the gap between the completion task and the mesh deformation algorithms. As far as we know, we are the first to refine the point cloud completion task by mimicing traditional graphics algorithms with GCN-guided deformation. We have conducted extensive experiments on both the simulated indoor dataset ShapeNet, outdoor dataset KITTI, and our self-collected autonomous driving dataset Pandar40. The results show that our method outperforms the existing state-of-the-art algorithms in the 3D point cloud completion task.

Abstract P378: Automated Estimation of Ischemic Core Volume on Non-Contrast-Enhanced Computed Tomography via Machine Learning

Background and Purpose: Accurate estimation of ischemic core on baseline imaging has treatment implications in patients with acute ischemic stroke (AIS). Machine learning (ML) algorithms have shown promising results in estimating ischemic core using routine non-contrast CT (NCCT). We used a ML-trained algorithm to quantify ischemic core volume on NCCT and compared the results to concurrent diffusion MRI as the reference standard in patients with AIS. Methods: We analyzed consecutive anterior circulation AIS patients who had baseline (pretreatment) NCCT and MRI (DWI). Ischemic lesion volume was calculated on MRI-DWI using an automated software (Olea Medical SAS, La Ciotat, France). An automatic segmentation approach using a combination of traditional 3D graphics and statistical methods, and ML classification techniques (Brainomix, Oxford, United Kingdom) was used to identify ischemic core voxels on NCCT. Total ischemic core volumes on ML-NCCT and DWI-MR were quantitatively compared by Bland-Altman plots and Pearson correlation. Results: A total of 50 patients (27 female, 23 male, mean age 72.6 years) were included. Baseline imaging was performed within 173 ± 143 minutes (mean ± SD) from symptom onset. The mean time difference between MRI and NCCT was 72 min. The baseline NIHSS was 14, 8-21 (Median, IQR). Algorithm-segmented ischemic core volume detected on NCCT was median 12.7 mL, IQR 3.5-26.0 mL. Ischemic core volume on DWI MRI was median 8.8 mL, IQR 3.2-34.0 mL. ML-NCCT core volumes significantly correlated with DWI MRI core volumes, r =0.61, p <0.001. The mean difference between the ML-NCCT and DWI MRI core volumes was 12.4 mL, p =0.81. For the reperfusion treatment threshold of an ischemic core volume within 70 mL, while no patients would have been excluded using our algorithm, five patients would have been incorrectly dichotomized as having an ischemic volume of <70 mL compared to MRI. Conclusion: This ML-approach accurately quantifies ischemic core volume on NCCT compared to the reference standard of diffusion MRI in patients with AIS.

An integrated approach of Active Incremental fine-tuning, SegNet, and CRF for cutting tool wearing areas segmentation with small samples

Cutting tool wear is a critical factor that affects product quality in manufacturing processes and measuring the flank wear area is the most common method to assess the condition of the tool. Nowadays, the direct way based on image processing has been developed due to its high information content and does not rely on expensive subsidiary measurement equipment compared with the indirect way. However, the direct way, whether based on computer graphics or based on artificial intelligence, has a shortcoming. The traditional computer graphics methods have poor robustness, and the artificial intelligence way enabled with deep convolutional neural networks (DCNN) requires a large amount of data and it usually works well on its training data. This article proposes a new architecture based on active incremental fine-tuning, SegNet, and CRF. The new architecture integrates active incremental fine-tuning and conditional random field with an optimized SegNet. The new architecture has greatly improved the running speed and reduced the model size. Moreover, the architecture can be trained with small samples and obtain high precision. Finally, in our case, the architecture achieves an average accuracy rate of about 88% on a small dataset. The training process consumes about 4612 s, and the number of learning parameters is reduced to 788,006. The methodology in the article has been verified through experiments.

RETRACTED: Development and application of VR course resources based on embedded system in open education

Virtual Reality VR technology offers a unique approach to enhance the use of complex 3D graphics and visualization environments. The study conducted using virtual reality (VR) technology integrated into the computer-aided design network; VR is a Web-based learning environment. Virtual reality technology is expected to be a traditional 2D computer graphics (CG) CG extended to a 3D real-time simulation program. Virtual reality technology can be used to promote participation and student learning. With VR education, change the delivery of educational content. No user interaction is well suited to see it and is very suitable to create a real or imaginary virtual world. Immersive virtual reality (VR) applications require ultra-high data rate and low latency to run smoothly, designed to improve multiuser wireless VR video (depth of learning support system) VR experiences. It has been proposed streaming: quality and low-latency video block submission. Scenario, VR is that it can describe some fields to be widely applied to education. One of the main features of VR is that it allows for multisensory interaction in the visualization space. This combination of visualization and interactive cosmetic VR of multisensory is, ideally, to see whether suitable for effective learning and try to explain this effect by the benefits of active learning from experience. Also, may want to consider some of the defenders and the application of VR education related to technology-related lottery.