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

要旨

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 place large shadow regions to create a realistic volumetric presentation while the final results can vary dramatically depending on their “staging” and “attention guiding” needs. We discovered they would accept AI suggestions for less engaging semantic parts or landscaping, while needing the capability to adjust details. Based on our observations, we developed ShadowMagic, which (1) generates AI-driven shadows based on commonly used light directions, (2) enables users to selectively choose results depending on semantics, and (3) allows users to complete shadow areas themselves for further perfection. Through a summative evaluation with 5 professionals, we found that they were significantly more satisfied with our AI-driven results compared to a baseline. We also found that ShadowMagic’s “step by step” workflow helps participants more easily adopt AI-driven results. We conclude by providing implications.

著者
Amrita Ganguly
George Mason University, Fairfax, Virginia, United States
Chuan Yan
George Mason University, CENTREVILLE, Virginia, United States
John Joon Young. Chung
Midjourney, San Francisco, California, United States
Tong Steven. Sun
George Mason University, Fairfax, Virginia, United States
YOON KIHEON
Pusan National University, Pusan, Korea, Republic of
Yotam Gingold
George Mason University, Fairfax, Virginia, United States
Sungsoo Ray Hong
George Mason University, Fairfax, Virginia, United States
論文URL

https://doi.org/10.1145/3654777.3676332

動画

会議: UIST 2024

ACM Symposium on User Interface Software and Technology

セッション: 3. Generating Visuals

Westin: Allegheny 3
4 件の発表
2024-10-16 18:00:00
2024-10-16 19:00:00