# Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1705.01908 · HTML: https://mlsanity.com/paper/1705.01908/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2017.

## Built on by (most cited first, 6 of 6)

- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design](https://mlsanity.com/paper/2504.13176/) (2025)
- [Large-scale optimal transport map estimation using projection pursuit](https://mlsanity.com/paper/2106.05838/) (2021)
- [GAN Computers Generate Arts? A Survey on Visual Arts, Music, and Literary Text Generation using Generative Adversarial Network](https://mlsanity.com/paper/2108.03857/) (2021)
- [Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks](https://mlsanity.com/paper/2107.07943/) (2021)
- [Shapes2Toon: Generating Cartoon Characters from Simple Geometric Shapes](https://mlsanity.com/paper/2211.02141/) (2022)

## Abstract (arXiv)

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Images can be generated at the pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a potential application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose the auto-painter model which can automatically generate compatible colors for a sketch. The new model is not only capable of painting hand-draw sketch with proper colors, but also allowing users to indicate preferred colors. Experimental results on two sketch datasets show that the auto-painter performs better that existing image-to-image methods.