The Applicability of Two Generative Adversarial Networks to Generative Plantscape Design: A Comparative Study

• Published in: Land (Basel) Vol. 14; no. 4; p. 746
• Main Authors: Feng, Lu, Sun, Yuting, Yu, Chenwen, Chen, Ran, Zhao, Jing
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2025
• Subjects: Aesthetics; Algorithms; Artificial intelligence; Automation; Comparative analysis; Comparative studies; Datasets; Deep learning; Design; Design optimization; Designers; Efficiency; flower border; Flowers; Flowers & plants; generative adversarial network; Generative adversarial networks; Image quality; Landscape architecture; Machine learning; Neural networks; plantscape design; Technology application; Training; Urban planning; China
• ISSN: 2073-445X; 2073-445X
• DOI: 10.3390/land14040746

Plantscape design combines both scientific and technical elements, with flower borders serving as a representative example. Generative Adversarial Networks (GANs), which can automatically generate images through training, offer new technological support for plantscape design, potentially enhancing the efficiency of designers. This study focuses on flower border plans as the research subject and creates a dataset of flower border designs. Subsequently, the research employed two algorithms, Pix2Pix and CycleGAN, for training and testing, enabling the automatic generation of flower border design images, with subsequent optimization of the results. The paper compares the generated results of both algorithms in terms of image quality and design patterns, providing both objective and subjective evaluations of CycleGAN, which performed better. Experimental results show that the algorithm can learn the latent patterns of flower border design to some extent and generate high-quality images with reasonable performance in terms of ornamental character and ecological character. Among the design types, bar-shaped layouts showed the best results. However, the algorithm still faces challenges in handling complex site processing, boundary clarity, and design innovation. Additionally, aspects such as vertical variation, texture harmony, low maintenance, and sustainability remain areas for future improvement. This study demonstrates the potential of GAN in small-scale plantscape design and offers innovative and feasible solutions for flower border design.