Stroke-based rendering aims to recreate an image with a set of strokes. Most existing methods render complex images using an uniform-block-dividing strategy, which leads to boundary inconsistency artifacts. To solve the problem, we propose Compositional Neural Painter, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions. We start from an empty canvas and divide the painting process into several steps. At each step, a compositor network trained with a phasic RL strategy first predicts the next painting region, then a painter network trained with a WGAN discriminator predicts stroke parameters, and a stroke renderer paints the strokes onto the painting region of the current canvas. Moreover, we extend our method to stroke-based style transfer with a novel differentiable distance transform loss, which helps preserve the structure of the input image during stroke-based stylization. Extensive experiments show our model outperforms the existing models in both stroke-based neural painting and stroke-based stylization. Code is available at https://github.com/sjtuplayer/Compositional_Neural_Painter

通过动态预测下一次绘画区域、预测画笔参数以及将笔触渲染到当前画布的绘画过程，提出了基于组合神经绘画家的stroke-based rendering框架，还借助可微分距离变换损失将该方法扩展到基于stroke的风格迁移，实验证明在stroke-based neural painting和stroke-based stylization方面，我们的模型优于现有模型。

基于笔画的神经绘画和风格化技术与动态预测的绘画区域