Stroke-based Rendering: From Heuristics to Deep Learning
It provides a structured introduction to stroke-based rendering for researchers and practitioners in AI and computer graphics, but it is incremental as it is a survey paper.
The paper surveys stroke-based rendering algorithms, which tackle the problem of generating artworks through planned sequences of shapes and strokes rather than pixel-based methods, bridging the gap between human artistic processes and deep learning models.
In the last few years, artistic image-making with deep learning models has gained a considerable amount of traction. A large number of these models operate directly in the pixel space and generate raster images. This is however not how most humans would produce artworks, for example, by planning a sequence of shapes and strokes to draw. Recent developments in deep learning methods help to bridge the gap between stroke-based paintings and pixel photo generation. With this survey, we aim to provide a structured introduction and understanding of common challenges and approaches in stroke-based rendering algorithms. These algorithms range from simple rule-based heuristics to stroke optimization and deep reinforcement agents, trained to paint images with differentiable vector graphics and neural rendering.