Answers are grounded in this paper and cite their sources.
Introduction: Public art in urban spaces enhances aesthetics, reflects cultural identity, fosters community engagement, and contributes to place making, transforming everyday environments into meaningful, interactive public experiences. Limitations include a lack of deep learning applications in extracting public art elements, limited exploration of cultural integration, and insufficient focus on interactive design methods.Methods: The proposed Great Cane Rat Algorithm-Tuned Scalable Generative Adversarial Network (GCR-SGAN) optimizes SGAN performance using GCRO for generating high-quality public art designs. The dataset includes images of public art, featuring murals, sculptures, and design elements for training and analysis. Histogram equalization will enhance image contrast, improving details, while Visual Geometry Group 16 (VGG16) feature extraction will capture high-level visual patterns and features, creating a robust representation for subsequent analysis and model training. The proposed work integrates SGAN for generating high-quality public art designs with GCR optimization to enhance GAN training, improving convergence stability, generation quality, and scalability for effective art design generation and analysis. Results: The results demonstrate that the GCR-SGAN model had accuracy of 0.98, which efficiently generates high-quality public art designs, optimizing both visual appeal and training stability. Conclusion: The approach effectively advances the generation of diverse, scalable art for real-world applications.conclusions: This research is to apply deep learning techniques to extract and analyze elements of public art in Suzhou Subway, exploring their cultural significance, design patterns, and potential applications in urban planning, enhancing the aesthetic and functional aspects of subway spaces.
No takes yet. Share an insight, caveat, or question.
Yu Huang (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: