Advancing Architectural Design Through Generative Adversarial Network Deep Learning Technology
Year: 2024
Type: article
Abstract: Recent advancements in deep learning have popularized Generative Adversarial Networks for image generation. This study investigates integrating Generative Adversarial Networks technology into architectural design to empower architects in creating diverse, innovative, and practical designs. By analyzing architectural research, deep learning theory, and practical Generative Adversarial Networks applications, we substantiate the feasibility of using Generative Adversarial Networks for architectural design optimization. The generated architectural images exhibit significant diversity, innovation, and practicality, inspiring architects with numerous design possibilities. Overall, Generative Adversarial Networks technology not only expands design methodologies but also stimulates groundbreaking innovation in architectural practice. As technology progresses, Generative Adversarial Networks-based architectural design optimization shows promising potential for widespread adoption, heralding a new era of creativity and efficiency in architecture.
DOI: 10.4018/ijdst.353305
Authors: Yueming Huang, Jianhua He
Language: English
Subfield: Architecture
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4401995960