# AutoToon: Automatic Geometric Warping for Face Cartoon Generation

arXiv: https://arxiv.org/abs/2004.02377 · HTML: https://mlsanity.com/paper/2004.02377/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 12 of 12)

- [Deformable One-shot Face Stylization via DINO Semantic Guidance](https://mlsanity.com/paper/2403.00459/) (2024)
- [DemoCaricature: Democratising Caricature Generation with a Rough Sketch](https://mlsanity.com/paper/2312.04364/) (2023)
- [StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation](https://mlsanity.com/paper/2107.04331/) (2021)
- [DCT-Net: Domain-Calibrated Translation for Portrait Stylization](https://mlsanity.com/paper/2207.02426/) (2022)
- [StyO: Stylize Your Face in Only One-shot](https://mlsanity.com/paper/2303.03231/) (2023)
- [Generalizable Face Landmarking Guided by Conditional Face Warping](https://mlsanity.com/paper/2404.12322/) (2024)
- [Fix the Noise: Disentangling Source Feature for Controllable Domain Translation](https://mlsanity.com/paper/2303.11545/) (2023)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps](https://mlsanity.com/paper/2206.02903/) (2022)
- [Shapes2Toon: Generating Cartoon Characters from Simple Geometric Shapes](https://mlsanity.com/paper/2211.02141/) (2022)
- [High-Quality Face Caricature via Style Translation](https://mlsanity.com/paper/2311.13338/) (2023)
- [CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis](https://mlsanity.com/paper/2606.13964/) (2026)

## Abstract (arXiv)

Caricature, a type of exaggerated artistic portrait, amplifies the distinctive, yet nuanced traits of human faces. This task is typically left to artists, as it has proven difficult to capture subjects' unique characteristics well using automated methods. Recent development of deep end-to-end methods has achieved promising results in capturing style and higher-level exaggerations. However, a key part of caricatures, face warping, has remained challenging for these systems. In this work, we propose AutoToon, the first supervised deep learning method that yields high-quality warps for the warping component of caricatures. Completely disentangled from style, it can be paired with any stylization method to create diverse caricatures. In contrast to prior art, we leverage an SENet and spatial transformer module and train directly on artist warping fields, applying losses both prior to and after warping. As shown by our user studies, we achieve appealing exaggerations that amplify distinguishing features of the face while preserving facial detail.