WarpGAN: Automatic Caricature Generation

Yichun Shi, Debayan Deb, Anil K. Jain
11/25/2018
cs.CV

Official code: seasonSH/WarpGAN (260 stars, MIT, last commit 2019-04-16).

Abstract

We propose, WarpGAN, a fully automatic network that can generate caricatures given an input face photo. Besides transferring rich texture styles, WarpGAN learns to automatically predict a set of control points that can warp the photo into a caricature, while preserving identity. We introduce an identity-preserving adversarial loss that aids the discriminator to distinguish between different subjects. Moreover, WarpGAN allows customization of the generated caricatures by controlling the exaggeration extent and the visual styles. Experimental results on a public domain dataset, WebCaricature, show that WarpGAN is capable of generating a diverse set of caricatures while preserving the identities. Five caricature experts suggest that caricatures generated by WarpGAN are visually similar to hand-drawn ones and only prominent facial features are exaggerated.

View on arXivView PDF

Code Implementations(1)

seasonSH/WarpGANOfficial100%
MIT

(CVPR 2019 Oral) Style Transfer with Geometric Deformation

26061PythonApr 1, 20197 years agoMIT
caricaturescartoonganstyle-transfer

Similar Papers

CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth

91% match1 repo52025

High-Quality Face Caricature via Style Translation

88% match2023

DemoCaricature: Democratising Caricature Generation with a Rough Sketch

83% match2023

Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning

82% match2023

Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs

82% match1 repo932017

StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation

81% match1 repo7212024

Cite this paper

@article{shi2018warpgan,
  title  = {WarpGAN: Automatic Caricature Generation},
  author = {Yichun Shi and Debayan Deb and Anil K. Jain},
  year   = {2018},
  eprint = {1811.10100},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1811.10100}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1811.10100.svg)](https://codeofpaper.com/paper/1811.10100)

Discussion