Video
BibTex
@inproceedings{Alghofaili:2021:10.20380/GI2021.08,
author = {Alghofaili, Rawan and Fisher, Matthew and Zhang, Richard and Luk{\'a}{\v c}, Michal and Yu, Lap-Fai},
title = {Exploring Sketch-based Character Design Guided by Automatic Colorization},
booktitle = {Proceedings of Graphics Interface 2021},
series = {GI 2021},
year = {2021},
issn = {0713-5424},
isbn = {978-0-9947868-6-9},
location = {Virtual Event},
pages = {56 -- 67},
numpages = {12},
doi = {10.20380/GI2021.08},
publisher = {Canadian Information Processing Society},
}
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.