Yan Mengran, Tang Chun, Yan Jida, Surip Siti Suhaily
Fine Arts Department, Bozhou University, Bozhou City, Anhui Province, China.
Product Design Department, School of The Arts, Universiti Sains Malaysia, Penang, Malaysia.
PeerJ Comput Sci. 2025 Mar 7;11:e2732. doi: 10.7717/peerj-cs.2732. eCollection 2025.
Pattern design is essential in various domains, especially in traditional lantern production, where patterns convey cultural history and artistic values. Our research presents an innovative generative model that produces customizable lantern patterns, integrating classical aesthetics with modern design features a generative adversarial network (GAN)-based framework. The model was trained on an extensive dataset of over 17,000 pattern images over ten various categories. Experimental assessment demonstrates the model's remarkable proficiency, achieving an Inception Score of 5.259, much surpassing the performance of other GAN-based approaches. This exceptional result demonstrates the effective integration of traditional pattern elements with AI-driven design processes. The model offers enhanced design flexibility noise vector hybridization and post-processing techniques, allowing for accurate control over pattern production while preserving cultural authenticity. These capabilities make our model a valuable tool for modernizing lantern pattern design while maintaining classic artistic elements.
图案设计在各个领域都至关重要，尤其是在传统灯笼制作中，图案承载着文化历史和艺术价值。我们的研究提出了一种创新的生成模型，该模型可生成可定制的灯笼图案，将古典美学与现代设计特征相结合——这是一个基于生成对抗网络（GAN）的框架。该模型在包含十个不同类别的超过17000张图案图像的广泛数据集上进行了训练。实验评估表明该模型具有卓越的能力，获得了5.259的Inception分数，大大超越了其他基于GAN的方法的性能。这一出色结果证明了传统图案元素与人工智能驱动的设计过程的有效融合。该模型通过噪声向量混合和后处理技术提供了更高的设计灵活性，在保留文化真实性的同时，能够精确控制图案生成。这些能力使我们的模型成为在保持经典艺术元素的同时使灯笼图案设计现代化的宝贵工具。
