AutoToon: Automatic Geometric Warping for Face Cartoon Generation (WACV 2020)


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.

Paper | Code & Data

Supplementary Material

Citation (bibtex)

  author = {Gong, Julia and Hold-Geoffroy, Yannick and Lu, Jingwan},
  title = {AutoToon: Automatic Geometric Warping for Face Cartoon Generation},
  booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
  month = {March},
  year = {2020}


This research was completed during Julia Gong's internship at Adobe Research, where she had the fortune of being mentored by Yannick Hold-Geoffroy and Cynthia Lu. This work is patent-pending.

The documents contained in the directories of this work are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder, except when identified by Creative Commons License 2.0, in which case the license applies to both the original and modified versions of the images.