# GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning

arXiv: https://arxiv.org/abs/2508.09207 · HTML: https://mlsanity.com/paper/2508.09207/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Exploring the structure of a real-time, arbitrary neural artistic stylization network](https://mlsanity.com/paper/1705.06830/) (2017)
- [How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference](https://mlsanity.com/paper/2003.13593/) (2020)
- [Outline Colorization through Tandem Adversarial Networks](https://mlsanity.com/paper/1704.08834/) (2017)
- [FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning Techniques](https://mlsanity.com/paper/2003.09579/) (2020)

## Built on by (most cited first, 1 of 1)

- [Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition](https://mlsanity.com/paper/2509.00077/) (2025)

## Abstract (arXiv)

The process of generating fully colorized drawings from sketches is a large, usually costly bottleneck in the manga and anime industry. In this study, we examine multiple models for image-to-image translation between anime characters and their sketches, including Neural Style Transfer, C-GAN, and CycleGAN. By assessing them qualitatively and quantitatively, we find that C-GAN is the most effective model that is able to produce high-quality and high-resolution images close to those created by humans.