ShadowMagic: Designing Human-AI Collaborative Support for Comic Professionals’ Shadowing

Paper

ShadowMagic workflow: ShadowMagic accepts a flat color layer and a line drawing layer as input (a). ShadowMagic’s backend generates shadow suggestions based on a user’s light direction choice (b, left). ShadowMagic’s backend segments the flat regions into “semantic” segments, such as face, hair, or clothing (b, right). ShadowMagic’s frontend lets users filter by semantic region. Users can choose to either adopt the AI-suggested shadows (c, pink shadows on the left, a user decided to use suggestions on clothing and arms) or apply additional edits (c, blue face and clothing shadows on the right, drawn by a user). A final outcome combines pink and blue shadows (d). This refinement can increase shadowing efficiency while providing sufficient control for a user.

Abstract

Shadowing allows artists to convey realistic volume and emotion of characters in comic colorization. While AI technologies have the potential to improve professionals’ shadowing experience, current practice is manual and time-consuming. To understand how we can improve their shadowing experience, we conducted interviews with 5 professionals. We found that professionals’ level of engagement can vary depending on semantics, such as characters’ faces or hair. We also found they spent time on shadow “landscaping”—deciding where to put big shadow regions to make a realistic volumetric presentation— while the final results can dramatically vary depending on their “staging” and “attention guiding” needs. We found they would accept AI suggestions for less engaging semantic parts or landscaping, while they would need to have the capability to adjust details. Based on our observations, we built ShadowMagic that (1) generates AI-driven shadows based on typically used light directions, (2) enables a user to selectively choose the results depending on the semantics, and (3) allows users to finish shadow areas by themselves for further perfection. Through a summative evaluation with 5 professionals, we found that they were significantly more satisfied with our AI-driven results than a baseline. We also found ShadowMagic’s “step by step” workflow helps participants more easily adopt AI-driven results. We conclude by providing implications.

Video Overview (5 minutes)

Download as:

• 60 MB MP4 and subtitles (VTT)

BibTeX

@inproceedings{Ganguly:2024:ShadowMagic,
 author    = {Ganguly, Amrita and Yan, Chuan and Chung, John Joon Young and Sun, Tong Steven and Yoon, Kiheon and Gingold, Yotam and Hong, Sungsoo Ray},
 title     = {{S}hadow{M}agic: Designing Human-AI Collaborative Support for Comic Professionals' Shadowing},
 booktitle = {Proceedings of the ACM Symposium on User Interface Software and Technology},
 series    = {UIST},
 year      = {2024},
 keywords  = {Human-AI collaboration, Comic Shadowing, System for Professionals}
}