This study analyzes the process of integrating artificial intelligence (AI) content into a computergraphics (CG) course for architecture students at a Taiwanese university. The university places a high priority on AI...
详细信息
ISBN:
(纸本)9789819744411;9789819744428
This study analyzes the process of integrating artificial intelligence (AI) content into a computergraphics (CG) course for architecture students at a Taiwanese university. The university places a high priority on AI education, and students are required to pass an AI competency test to graduate. The CG course is well-suited for integrating AI components since it relies heavily on visualization and graphics. The study collected both quantitative and qualitative data to assess student reactions and learning outcomes with the new AI content. An end-of-course survey revealed very positive responses. 78-100% of students agreed that the course helped increase their knowledge of AI and awareness of its applications. Further insights were gathered through follow-up focus groups. Students were optimistic about AI learning and did not feel that it detracted from their core architecture studies. However, they suggested slowing down the pace of AI content delivery. While students acknowledged the potential for applying AI in areas like construction visualization, they had a limited view of its broader professional impacts. In summary, this exploratory study suggests that incorporating AI content into an existing technical course was well-received by students and may have improved engagement for struggling learners. However, careful integration is necessary to avoid overwhelming students with too much new material. The study also discusses implications for curriculum design theory and preparing students for AI's professional impacts.
Interactive dynamic simulators are an accelerator for developing novel robotic control algorithms and complex systems involving humans and robots. In user training and synthetic data generation applications, high-fide...
详细信息
ISBN:
(纸本)9798331521561;9798331521554
Interactive dynamic simulators are an accelerator for developing novel robotic control algorithms and complex systems involving humans and robots. In user training and synthetic data generation applications, high-fidelity visualizations from the simulation are essential. Yet, robotic simulators often limit their rendering algorithms to preserve real-time interaction with the simulation. Advancements in graphics Processing Units (GPU) enable improved visualization without compromising performance. However, these advancements cannot be fully leveraged in simulation frameworks that use legacy graphics application programming interfaces (API) to interface with the GPU. This paper presents a performance-focused and lightweight rendering engine supporting the modern Vulkan graphics API that can be easily integrated with other simulation frameworks to enhance visualizations. To illustrate the proposed method, our engine is used to modernize the legacy rendering pipeline of the Asynchronous Multi-Body Framework (AMBF), a dynamic simulation framework used extensively for interactive robotics simulation development. This new rendering engine implements graphical features such as physically based rendering (PBR), anti-aliasing, and ray-traced shadows, significantly improving the image fidelity of AMBF. Computational experiments show that the engine can render a simulated scene with over seven million triangles while maintaining GPU computation times within two milliseconds.
computergraphics (CG) rendering platforms produce imagery with ever-increasing photo realism. The narrowing domain gap between real and synthetic imagery makes it possible to use CG images as training data for deep l...
ISBN:
(纸本)9798350307184
computergraphics (CG) rendering platforms produce imagery with ever-increasing photo realism. The narrowing domain gap between real and synthetic imagery makes it possible to use CG images as training data for deep learning models targeting high-level computer vision tasks, such as autonomous driving and semantic segmentation. CG images, however, are currently not suitable for low-level vision tasks targeting RAW sensor images. This is because RAW images are encoded in sensor-specific color spaces and incur pre-white-balance color casts caused by the sensor's response to scene illumination. CG images are rendered directly to a device-independent perceptual color space without needing white balancing. As a result, it is necessary to apply a mapping procedure to close the domain gap between graphics and RAW images. To this end, we introduce a framework to process graphics images to mimic RAW sensor images accurately. Our approach allows a one-tomany mapping, where a single graphics image can be transformed to match multiple sensors and multiple scene illuminations. In addition, our approach requires only a handful of example RAW-DNG files from the target sensor as parameters for the mapping process. We compare our method to alternative strategies and show that our approach produces more realistic RAW images and provides better results on three low-level vision tasks: RAW denoising, illumination estimation, and neural rendering for night photography. Finally, as part of this work, we provide a dataset of 292 realistic CG images for training low-light imaging models.
The rapid development of digital media has influenced the change and update of technology, and mixed reality (MR) technology has gradually emerged. While people rely on digital media to obtain information, the extreme...
详细信息
Eye tracking has been used in many scientific fields, such as education, usability research, sports, psychology, and marketing. Often, visualization plays an important role in the analysis of eye tracking data. In the...
详细信息
ISBN:
(纸本)9783031601132;9783031601149
Eye tracking has been used in many scientific fields, such as education, usability research, sports, psychology, and marketing. Often, visualization plays an important role in the analysis of eye tracking data. In the past, linked micromap plots have been widely used to visualize geographic patterns of regions and subregions. Based on the idea of linked micromap plots, we introduce three different types of linked microposter plots to visualize the eye movement pattern when people are looking at different components (such as headings, tables, figures, and different sections of text) of scientific posters. These types are basic linked microposter plots, linked timeline microposter plots, and linked scanpath microposter plots. When using linked microposter plots, the eye tracking data of people looking at various poster components can be better and more easily interpreted. Linked timeline microposter plots and linked scanpath microposter plots are extensions of basic linked microposter plots. The scanpath time series information is included in the linked scanpath microposter plots visualization. The linked microposter plots and their extensions provide several features that overcome some of the disadvantages of previously existing eye tracking data visualization methods. The linked microposter plots can be created automatically using our EyeTrackR R package and can be easily extended to other applications.
Projection blurring and defocusing is a prevalent issue that can significantly degrade the quality and legibility of projected images and visual content. This paper introduces a novel method to address this problem th...
详细信息
A traditional computergraphics domain has received an unprecedented boost from the newest developments in generative Artificial Intelligence (GenAI). It affects all areas: from image generation, to face recognition, ...
详细信息
Virtual Reality (VR) applications constantly strive for more realism, immersion and intuitive user experiences. Traditional VR controllers can hinder full immersion, since they form an additional barrier between the u...
详细信息
Increasingly technical advancements have created new hurdles for industrial software development, this article proposes the validation of an architecture for the visualization of information through complex networks, ...
详细信息
暂无评论