Generative Adversarial Network Based on Self-Attention Mechanism for Automatic Page Layout Generation
Peng Fei Sun, Xiaomei Liu, Liguo Weng, Ziheng Liu · Applied Sciences · 2025
Automatic page layout generation is a challenging and promising research task, which improves the design efficiency and quality of various documents, web pages, etc. However, the current generation of layouts that are both reasonable and aesthetically pleasing still faces many difficulties, such as the shortcomings of existing methods in terms of structural rationality, element alignment, text and image relationship processing, and insufficient consideration of element details and mutual influence within the page. To address these issues, this article proposes a Transformer-based Generative Adversarial Network (TGAN). Generative Adversarial Networks (GANs) innovatively introduce the self-attention mechanism into the network, enabling the model to focus more on key local information that affects page layout. By introducing conditional variables in the generator and discriminator, more accurate sample generation and discrimination can be achieved. The experimental results show that the TGAN outperforms other methods in both subjective and objective ratings when generating page layouts. The generated layouts perform better in element alignment, avoiding overlap, and exhibit higher layout quality and stability, providing a more effective solution for automatic page layout generation.