Exploring Sketch-based Character Design Guided by Automatic Colorization

Rawan Alghofaili1, Matthew Fisher2, Richard Zhang2, Michal Lukáč2, Lap-Fai Yu1
1 George Mason University, 2Adobe Research
the image on the left shows a user sketching a cartoon character on a tablet. The image in the middle shows multiple colorizations of the character labeled as 'synthesized thumbnails' with one of the colorizations selected. On the right, a turnaround sheet is shown with similar coloring as the selected colorization thumbnail.

Our character exploration tool facilitates the character design process (more specifically, character exploration) by allowing artists to explore characters using colored thumbnails synthesized from sketches. These colored thumbnails, which are traditionally rough grey-scale sketches, better visualize the character for creating the turnaround sheet. The turnaround sheet was created from the selected thumbnail by Ruba Alhumaidi.

Abstract

Character design is a lengthy process, requiring artists to iteratively alter their characters' features and colorization schemes according to feedback from creative directors or peers. Artists experiment with multiple colorization schemes before deciding on the right color palette. This process may necessitate several tedious manual re-colorizations of the character. Any substantial changes to the character's appearance may also require manual re-colorization. Such complications motivate a computational approach for visualizing characters and drafting solutions.

We propose a character exploration tool that automatically colors a sketch based on a selected style. The tool employs a Generative Adversarial Network trained to automatically color sketches. The tool also allows a selection of faces to be used as a template for the character's design. We validated our tool by comparing it with using Photoshop for character exploration in our pilot study. Finally, we conducted a study to evaluate our tool's efficacy within the design pipeline.

Keywords

Sketching, Colorization, Generative design

Publication

2021, Rawan Alghofaili, Matthew Fisher, Richard Zhang, Michal Lukáč, Lap-Fai Yu
Exploring Sketch-based Character Design Guided by Automatic Colorization.

Paper(8 MB)
Supplementary Material (42 KB)

BibTex


@inproceedings{alghofaili2021exploring,
title={Exploring Sketch-based Character Design Guided by Automatic Colorization},
author={Rawan Alghofaili and Matthew Fisher and Richard Zhang and Michal Luk{\'a}{\v{c}} and Lap-Fai Yu},
booktitle={Graphics Interface 2021},
year={2021}
}

Acknowledgments

We are grateful for the anonymous reviewers for their constructive feed back. We thank Atheer AlKubeyyer and Mazen Almusaed for helping us formulate our problem statement. We would especially like to thank Ruba Alhumaidi for creating the artwork for this paper and regularly providing feedback to improve our prototype. The DCXR lab acknowledges the generous support of Adobe through unrestricted gifts. This project was supported by an NSF CAREER Award (award number: 1942531).