Sketch simplification based on conditional random field and least squares generative adversarial networks

Sketch simplification is a critical part of cartoon drawing work. Some existing approaches are already capable of simplifying simple sketches, but in some cases, they are still insufficient because of method diversity of sketch drawing and complexity of sketch content. In this paper, we present a novel approach of building the model for sketch simplification, which is based on the conditional random field (CRF) and Least Squares generative adversarial networks (LSGAN). Through the zero-sum game of the generator and the discriminator in the model and the restriction of the conditional random field, the model can generate the simplified images, which are more similar to standard line images. The dataset we build contains a large number of image pairs that are drawn in different painting ways and with different contents. Finally, experiments show that our approach can obtain better results than the state of the art approaches in sketch simplification.