arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2307.12122cs.CVcs.LGeess.IV

基于扩散-生成对抗网络的巴迪克图案合成

Synthesis of Batik Motifs using a Diffusion -- Generative Adversarial Network

Universitas Brawijaya(布劳爪哇大学)

One Octadion, Novanto Yudistira, Diva Kurnianingtyas

AI总结:

针对巴迪克图案合成需求,本研究结合StyleGAN2-Ada与扩散技术,调整模型架构并使用精心整理的数据集,可生成细节精细、艺术变化丰富的真实优质巴迪克图案,助力设计师提升效率、降低成本,相关数据与代码已开源。

摘要:

巴迪克(Batik)是艺术与工艺的独特融合,是印度尼西亚社会独具特色的艺术与技术创造。目前巴迪克图案的研究主要集中在分类领域,而进一步的研究可拓展至巴迪克图案的合成方向。生成对抗网络(GANs)是用于生成合成数据的重要深度学习模型,但通常面临结果稳定性与一致性方面的挑战。本研究聚焦于运用StyleGAN2-Ada与扩散(Diffusion)技术生成逼真、高质量的合成巴迪克图案。StyleGAN2-Ada是GAN模型的一个变体,可将图像中的风格与内容要素分离,而扩散技术则会向数据中引入随机噪声。在巴迪克研究场景下,StyleGAN2-Ada与扩散技术被用于生成逼真的合成巴迪克图案。本研究还对模型架构进行了调整,并使用了经过精心整理的巴迪克数据集。研究的核心目标是帮助巴迪克设计师或手工艺人制作独特且优质的巴迪克图案,同时提升生产效率、降低成本。基于定性与定量评估的结果表明,所测试的模型能够生成真实优质的巴迪克图案,细节更精细,艺术变化丰富。数据集与代码可通过以下链接获取:https://github.com/octadion/diffusion-stylegan2-ada-pytorch

英文摘要:

Batik, a unique blend of art and craftsmanship, is a distinct artistic and technological creation for Indonesian society. Research on batik motifs is primarily focused on classification. However, further studies may extend to the synthesis of batik patterns. Generative Adversarial Networks (GANs) have been an important deep learning model for generating synthetic data, but often face challenges in the stability and consistency of results. This research focuses on the use of StyleGAN2-Ada and Diffusion techniques to produce realistic and high-quality synthetic batik patterns. StyleGAN2-Ada is a variation of the GAN model that separates the style and content aspects in an image, whereas diffusion techniques introduce random noise into the data. In the context of batik, StyleGAN2-Ada and Diffusion are used to produce realistic synthetic batik patterns. This study also made adjustments to the model architecture and used a well-curated batik dataset. The main goal is to assist batik designers or craftsmen in producing unique and quality batik motifs with efficient production time and costs. Based on qualitative and quantitative evaluations, the results show that the model tested is capable of producing authentic and quality batik patterns, with finer details and rich artistic variations. The dataset and code can be accessed here:https://github.com/octadion/diffusion-stylegan2-ada-pytorch

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑