Creative Professionals and AI A

会議の名前
CHI 2024
Unlocking Creator-AI Synergy: Challenges, Requirements, and Design Opportunities in AI-Powered Short-Form Video Production
要旨

The emergence of AI-Powered Short-Form Video Generators (ASVG) has showcased the potential to streamline production time and foster creative ideas. Despite their widespread adoption, research has underexplored ASVG, especially from creators’ perspectives. To evaluate the role of ASVG as creator-centered collaborators, we conducted mixed-method research: (1) interviews (N = 17) and (2) a participatory design workshop (N = 12) with short-form video creators. In our interviews, we investigated creators’ production process and challenges in creating short-form videos. In participatory workshops, short-form video creators envisioned AI-powered video tools, addressing their requirements and AI collaboration perceptions. Our findings indicate ASVGs can provide various advantages including inspiration, swift access to video sources, and automated highlight generation. To put things in perspective, we also underscore concerns arising from AI collaboration, including potential creator identity dilution, reduced creative output, and information bubble. We also discuss design considerations when designing ASVG to retain their creative values.

著者
Jini Kim
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Hajun Kim
NEOWIZ, Seongnam-si, Gyeonggi-do, Korea, Republic of
論文URL

https://doi.org/10.1145/3613904.3642476

動画
ReelFramer: Human-AI Co-Creation for News-to-Video Translation
要旨

Short videos on social media are the dominant way young people consume content. News outlets aim to reach audiences through news reels---short videos conveying news---but struggle to translate traditional journalistic formats into short, entertaining videos. To translate news into social media reels, we support journalists in reframing the narrative. In literature, narrative framing is a high-level structure that shapes the overall presentation of a story. We identified three narrative framings for reels that adapt social media norms but preserve news value, each with a different balance of information and entertainment. We introduce ReelFramer, a human-AI co-creative system that helps journalists translate print articles into scripts and storyboards. ReelFramer supports exploring multiple narrative framings to find one appropriate to the story. AI suggests foundational narrative details, including characters, plot, setting, and key information. ReelFramer also supports visual framing; AI suggests character and visual detail designs before generating a full storyboard. Our studies show that narrative framing introduces the necessary diversity to translate various articles into reels, and establishing foundational details helps generate scripts that are more relevant and coherent. We also discuss the benefits of using narrative framing and foundational details in content retargeting.

著者
Sitong Wang
Columbia University, New York, New York, United States
Samia Menon
Columbia University, New York, New York, United States
Tao Long
Columbia University, New York, New York, United States
Keren Henderson
Syracuse University, Syracuse, New York, United States
Dingzeyu Li
Adobe Research, Seattle, Washington, United States
Kevin Crowston
Syracuse University, Syracuse, New York, United States
Mark Hansen
Columbia University, New York, New York, United States
Jeffrey V. Nickerson
Stevens Institute of Technology, Hoboken, New Jersey, United States
Lydia B. Chilton
Columbia University, New York, New York, United States
論文URL

https://doi.org/10.1145/3613904.3642868

動画
Understanding Nonlinear Collaboration between Human and AI Agents: A Co-design Framework for Creative Design
要旨

Creative design is a nonlinear process where designers generate diverse ideas in the pursuit of an open-ended goal and converge towards consensus through iterative remixing. In contrast, AI-powered design tools often employ a linear sequence of incremental and precise instructions to approximate design objectives. Such operations violate customary creative design practices and thus hinder AI agents' ability to complete creative design tasks. To explore better human-AI co-design tools, we first summarize human designers’ practices through a formative study with 12 design experts. Taking graphic design as a representative scenario, we formulate a nonlinear human-AI co-design framework and develop a proof-of-concept prototype, OptiMuse. We evaluate OptiMuse and validate the nonlinear framework through a comparative study. We notice a subconscious change in people's attitudes towards AI agents, shifting from perceiving them as mere executors to regarding them as opinionated colleagues. This shift effectively fostered the exploration and reflection processes of individual designers.

著者
Jiayi Zhou
Zhejiang University, Hangzhou, Zhejiang, China
Renzhong Li
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China
Junxiu Tang
Zhejiang University, Hangzhou, Zhejiang, China
Tan Tang
Zhejiang University, Hangzhou, Zhejiang, China
Haotian Li
The Hong Kong University of Science and Technology, Hong Kong, China
Weiwei Cui
Microsoft Research Asia, Beijing, China
Yingcai Wu
Zhejiang University, Hangzhou, Zhejiang, China
論文URL

https://doi.org/10.1145/3613904.3642812

動画
PlantoGraphy: Incorporating Iterative Design Process into Generative Artificial Intelligence for Landscape Rendering
要旨

Landscape renderings are realistic images of landscape sites, allowing stakeholders to perceive better and evaluate design ideas. While recent advances in Generative Artificial Intelligence (GAI) enable automated generation of landscape renderings, the end-to-end methods are not compatible with common design processes, leading to insufficient alignment with design idealizations and limited cohesion of iterative landscape design. Informed by a formative study for comprehending design requirements, we present PlantoGraphy, an iterative design system that allows for interactive configuration of GAI models to accommodate human-centered design practice. A two-stage pipeline is incorporated: first, the concretization module transforms conceptual ideas into concrete scene layouts with a domain-oriented large language model; and second, the illustration module converts scene layouts into realistic landscape renderings with a layout-guided diffusion model fine-tuned through Low-Rank Adaptation. PlantoGraphy has undergone a series of performance evaluations and user studies, demonstrating its effectiveness in landscape rendering generation and the high recognition of its interactive functionality.

著者
Rong Huang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
Haichuan Lin
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
Chuanzhang Chen
Lappeenranta-Lahti University of Technology, Lahti, Finland
Kang Zhang
Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
Wei Zeng
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
論文URL

https://doi.org/10.1145/3613904.3642824

動画
Fashioning Creative Expertise with Generative AI: Graphical Interfaces for Design Space Exploration Better Support Ideation Than Text Prompts
要旨

This paper investigates the potential impact of deep generative models on the work of creative professionals. We argue that current generative modeling tools lack critical features that would make them useful creativity support tools, and introduce our own tool, generative.fashion, which was designed with theoretical principles of design space exploration in mind. Through qualitative studies with fashion design apprentices, we demonstrate how generative.fashion supported both divergent and convergent thinking, and compare it with a state-of-the-art text-based interface using Stable Diffusion. In general, the apprentices preferred generative.fashion, citing the features explicitly designed to support ideation. In two follow-up studies, we provide quantitative results that support and expand on these insights. We conclude that text-only prompts in existing models restrict creative exploration, especially for novices. Our work demonstrates that interfaces which are theoretically aligned with principles of design space exploration are essential for unlocking the full creative potential of generative AI.

著者
Richard Lee. Davis
EPFL, Lausanne, Switzerland
Thiemo Wambsganss
Bern University of Applied Sciences, Bern, Switzerland
Wei Jiang
École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
Kevin Gonyop Kim
ETH Zurich, Zurich, Switzerland
Tanja Käser
EPFL, Lausanne, Switzerland
Pierre Dillenbourg
EPFL, Lausanne, Switzerland
論文URL

https://doi.org/10.1145/3613904.3642908

動画