A5103236698- Digital Media and Visual Art
- Color perception and design
- Aesthetic Perception and Analysis
- Architecture and Computational Design
- BIM and Construction Integration
- Design Education and Practice
- Multisensory perception and integration
- Image Retrieval and Classification Techniques
- Advanced Manufacturing and Logistics Optimization
- Architecture, Design, and Social History
Macau University of Science and Technology
2023-2025
The exceptional architecture designed by master architects is a shared treasure of humanity, which embodies their design skills and concepts not possessed common architectural designers. To help ordinary designers improve the quality, we propose new artificial intelligence (AI) method for generative design, generates designs with specified styles architect quality through diffusion model based on textual prompts requirements. Compared to conventional methods dependent heavy intellectual...
Because interior design is subject to inefficiency, more creativity imperative. Due the development of artificial intelligence diffusion models, utilization text descriptions for generation creative designs has become a novel method solving aforementioned problem. Herein, we build unique decoration style dataset. Thus, solve problem pertaining need datasets, propose new loss function that considers style, and retrain model using this The trained learns knowledge can generate an through text....
Abstract The interior design suffers from inefficiency and a lack of aesthetic appeal. With the development artificial intelligence diffusion models, using text descriptions to generate aesthetically pleasing designs has emerged as new approach address these issues. In this study, we propose novel method based on model, which can quickly visually appealing input while allowing for specification decorative styles spatial functions. proposed in study creates creative drawings by computer...
Interior design requires designer creativity and significant workforce investments. Meanwhile, Artificial Intelligence (AI) is crucial for enhancing the efficiency of interior design. Therefore, this study proposes an innovative method to generate multistyle videos with AI. First, created a new indoor dataset train AI that can specified style. Subsequently, video generation super-resolution modules are integrated establish end-to-end workflow generates from texture-free 3D models. The...
In response to the challenges of low accuracy in traditional pepper blight identification under natural complex conditions, particularly detecting subtle infections on early-stage leaves, stems, and fruits. This study proposes a multi-site disease image recognition algorithm based YOLOv8, named MSPB-YOLO. effectively locates different infection sites peppers. By incorporating RVB-EMA module into model, we can significantly reduce interference from shallow noise high-resolution depth layers....
Abstract Interior designers are suffering from a lack of intelligent design methods. This study aims to enhance the accuracy and efficiency retrieval textures for interior design, which is crucial step toward design. Currently, rely on repetitive tasks obtain websites, ineffective as often requires hundreds textures. To address this issue, proposes hybrid deep learning approach, HyNet, boosts by recommending similar instead blindly searching. Additionally, new indoor texture dataset created...
The construction industry consumes a great deal of energy and causes environmental pollution, especially the interior design because lower degree automation brings more ecological problems. Thus, intelligent automated manufacturing are essential for design, as they can increase efficiency reduce pollution sustainable development. This study proposes new method automatic based on Grasshopper (GH) proves its effectiveness in through practice. proposed automatically generates suitable drawings...