Measuring the Degree of Beauty based on Alexander's 15 Properties of Living Structure

<p dir="ltr">This supplementary dataset accompanies the Master's thesis, <b><i>Characterizing Architectural and Urban Beauty from the Perspective of Living Structure Using AI and Geospatial Big Data</i></b>, authored by Andy Jingqian Xue at HKUST(GZ). The dataset is organized into three distinct parts:</p><p dir="ltr"><b>1. ScenicOrNot Dataset</b>: This collection of urban and architectural images is designed to validate the novel Large Language Model (LLM) approach for quantifying aesthetic beauty, as proposed in the thesis.</p><p dir="ltr"> - architectual_images.rar (1.4GB): Subset focusing on architectural images</p><p dir="ltr"> - all_images.csv (16MB): Comprehensive ratings and annotations for all images</p><p dir="ltr"> - archi_images.csv (1.4MB): Specific ratings and annotations for architectural images</p><p dir="ltr"> - 1000_pairs.csv (15KB): Contains 1000 image pairs for comparative analysis</p><p dir="ltr"><i> Note: Due to their large size, all images can be downloaded using the URLs provided in all_images.csv.</i></p><p dir="ltr"><b>2. Architectural Style Dataset</b>: This dataset facilitates a comparative study of architectural beauty, specifically examining the perceived decline in aesthetic value from traditional Western architectural styles to modern and contemporary designs.</p><p dir="ltr"> - images.rar (1.1GB): Collection of architectural images across different styles</p><p dir="ltr"> - style_pairs.csv (275KB): IDs for architectural style comparisons, 1500 paris in total</p><p dir="ltr"><b>3. Urban Function Dataset</b>: This part provides data to analyze the heterogeneity of beauty across various urban forms and functional zones.</p><p dir="ltr"> - images.zip (74MB): Collection of images representing different urban functions</p><p dir="ltr">The dataset serves as a comprehensive resource for studying urban and architectural beauty through the lens of living structure theory, combining traditional aesthetic analysis with modern AI approaches.</p>