General virtual sketching framework for vector line art

What is it about?

Vector line art plays an important role in graphic design, however, it is tedious to manually create. We introduce a general framework to produce line drawings from a wide variety of images, by learning a mapping from raster image space to vector image space. Our approach is based on a recurrent neural network that draws the lines one by one. A differentiable rasterization module allows for training with only supervised raster data. We use a dynamic window around a virtual pen while drawing lines, implemented with a proposed aligned cropping and differentiable pasting modules. Furthermore, we develop a stroke regularization loss that encourages the model to use fewer and longer strokes to simplify the resulting vector image. Ablation studies and comparisons with existing methods corroborate the efficiency of our approach which is able to generate visually better results in less computation time, while generalizing better to a diversity of images and applications.

Featured Image

Photo by Nicolás Pinilla on Unsplash

Photo by Nicolás Pinilla on Unsplash

Why is it important?

The main contributions of this work are summarized as follows: (1) A general framework for vector line drawing generation that works with a wide variety of images, dependent exclusively on raster training data. (2) A dynamic window mechanism that allows processing images of arbitrary resolution and high complexity. (3) Stroke regularization mechanism that controls the simplicity of the output vector images. (4) In depth comparison with existing approaches in a diversity of tasks.