Future cities imagined by ChatGPT-4o: human evaluation using...
Despite the growing integration of artificial intelligence (AI) into human society, a significant gap remains in understanding how AI can use its database-driven imagination to enhance urban planning and aesthetics effectively. This study explores ChatGPT-4o’s potential in generating future urban designs by incorporating human evaluations.
Key Findings
Using a mixed-methods design, the study identified key indicators for evaluating AI-generated urban design images and then applied Importance-Performance Analysis (IPA) to measure participants’ evaluations of these indicators. Results showed that creativity was the most critical indicator needing improvement, while technological sense received high performance.
Surprisingly, indicators like traffic rationality, environmental greening, public space utilization, and cultural representation were deemed less important. These findings suggest that participants prefer AI to focus more on bold, imaginative aspects. This study constructs a framework for evaluating AI-generated urban design images and offers valuable insights for improving AI applications in urban planning and image generation.
Applications of Large Language Models
Large language models, equipped with powerful natural language processing capabilities, have demonstrated impressive applications across diverse fields, highlighting their potential as valuable assistive tools. Research shows that large language models can generate illustrative images from text descriptions, aiding human creativity in art and design.
By transforming text descriptions into visual outputs, these models represent a significant advancement in AI’s capacity to interpret and visualize abstract concepts. Building on these developments, ChatGPT-4o incorporates multimodal functionality, enabling it to generate images of futuristic urban landscapes from specific text prompts, showcasing unique potential in urban planning and design.
Image Generation Capability
ChatGPT-4o’s image generation capability relies on an extensive database and robust computational capacity, enabling it to produce complex future city images from textual instructions. The high quality of this data directly impacts the model’s ability to generate detailed, accurate images.
Supported by deep learning algorithms, ChatGPT-4o’s generation process includes multi-layered language comprehension, image analysis, and cross-modal integration.
For more information, you can visit the original article on Humanities and Social Sciences Communications.
