基于创意序列学习的艺术风格学习与绘制系统

Creative Sequential Data Learning Method for Artistic Stylisation and Rendering System

在众多传统艺术绘画形式中,笔触是被现代计算机绘画工具(GIMP、Photoshop和Painter)普遍采用的形式之一.创新性地提出了服务于非真实感渲染AI辅助艺术创作系统(A4).系统能够实现自动生成特定艺术家风格的笔触效果.该系统在强化学习框架下,主要进行以下研究工作:(1)提出基于PGPE的正则化策略学习方法以提高风格学习过程的稳定性;(2)利用IRL(inverse reinforcement learning)算法实现了艺术风格行为的模型化及其数字化保护方法.实验结果表明,所提方法行之有效地实现了针对具体个性风格的照片水墨画艺术风格转化.

Among various traditional art forms,brush stroke drawing is one of the widely used styles in modern computer graphic tools such as GIMP,Photoshop and Painter.In this paper,an AI-aided art authoring（A4）system of non-photorealistic rendering is developed that allows users to automatically generate brush stroke paintings in a specific artist＇s style.Within the reinforcement learning framework of brush stroke generation,the first contribution in this paper is the application of regularized policy gradient method,which is more suitable for the stroke generation task.The other contribution is to learn artists＇ drawing styles from video-captured stroke data by inverse reinforcement learning.Experiments demonstrate that the presented system can successfully learn artists＇ styles and render pictures with consistent and smooth brush strokes.