Generative AI for Design

会議の名前
CHI 2024
The Effects of Generative AI on Design Fixation and Divergent Thinking
要旨

Generative AI systems have been heralded as tools for augmenting human creativity and inspiring divergent thinking, though with little empirical evidence for these claims. This paper explores the effects of exposure to AI-generated images on measures of design fixation and divergent thinking in a visual ideation task. Through a between-participants experiment (N=60), we found that support from an AI image generator during ideation leads to higher fixation on an initial example. Participants who used AI produced fewer ideas, with less variety and lower originality compared to a baseline. Our qualitative analysis suggests that the effectiveness of co-ideation with AI rests on participants' chosen approach to prompt creation and on the strategies used by participants to generate ideas in response to the AI's suggestions. We discuss opportunities for designing generative AI systems for ideation support and incorporating these AI tools into ideation workflows.

著者
Samangi Wadinambiarachchi
University of Melbourne, Melbourne, VIC, Australia
Ryan M.. Kelly
University of Melbourne, Melbourne, VIC, Australia
Saumya Pareek
University of Melbourne, Melbourne, Victoria, Australia
Qiushi Zhou
University of Melbourne, Melbourne, Victoria, Australia
Eduardo Velloso
University of Melbourne, Melbourne, Victoria, Australia
論文URL

https://doi.org/10.1145/3613904.3642919

動画
Beyond Numbers: Creating Analogies to Enhance Data Comprehension and Communication with Generative AI
要旨

Unfamiliar measurements usually hinder readers from grasping the scale of the numerical data, understanding the content, and feeling engaged with the context. To enhance data comprehension and communication, we leverage analogies to bridge the gap between abstract data and familiar measurements. In this work, we first conduct semi-structured interviews with design experts to identify design problems and summarize design considerations. Then, we collect an analogy dataset of 138 cases from various online sources. Based on the collected dataset, we characterize a design space for creating data analogies. Next, we build a prototype system, AnalogyMate, that automatically suggests data analogies, their corresponding design solutions, and generated visual representations powered by generative AI. The study results show the usefulness of AnalogyMate in aiding the creation process of data analogies and the effectiveness of data analogy in enhancing data comprehension and communication.

著者
Qing Chen
Tongji University, Shanghai, China
Wei Shuai
Tongji University, Shanghai, China
Jiyao Zhang
Tongji University, Shanghai, China
Zhida Sun
Shenzhen University, Shenzhen, China
Nan Cao
Tongji College of Design and Innovation, Shanghai, China
論文URL

https://doi.org/10.1145/3613904.3642480

動画
RoomDreaming: Generative-AI Approach to Facilitating Iterative, Preliminary Interior Design Exploration
要旨

Interior design aims to create aesthetically pleasing and functional environments within an architectural space. For a simple room, the preliminary design exploration currently takes multiple meetings and days of work for interior designers to incorporate homeowners' personal preferences through layout, furnishings, form, colors, and materials. We present RoomDreaming, a generative AI-based approach designed to facilitate preliminary interior design exploration. It empowers owners and designers to rapidly and efficiently iterate through a broad range of AI-generated, photo-realistic design alternatives, each uniquely tailored to fit actual space layouts and individual design preferences. We conducted a series of formative and summative studies with a total of 18 homeowners and 20 interior designers to help design, improve, and evaluate RoomDreaming. Owners reported that RoomDreaming effectively increased the breadth and depth of design exploration with higher efficiency and satisfaction. Designers reported that one hour of collaborative designing with RoomDreaming yielded results comparable to several days of traditional owner-designer meetings, plus days to weeks worth of designer work to develop and refine designs.

著者
Shun-Yu Wang
National Taiwan University, Taipei, Taiwan
Wei-Chung Su
National Taiwan University, Taipei, Taiwan
Serena Chen
University of California - San Diego, La Jolla, California, United States
Marta Misztal
Queen Mary University of London, London, United Kingdom
Katherine M.. Cheng
University of California, Berkeley, Berkeley, California, United States
Alwena Lin
University of California, Los Angeles , Los Angeles, California, United States
Yu Chen
National Taiwan University, Taipei, Taiwan
Ching-Yi Tsai
National Taiwan University, Taipei, Taiwan
Mike Y.. Chen
National Taiwan University, Taipei, Taiwan
論文URL

https://doi.org/10.1145/3613904.3642901

動画
Design Principles for Generative AI Applications
要旨

Generative AI applications present unique design challenges. As generative AI technologies are increasingly being incorporated into mainstream applications, there is an urgent need for guidance on how to design user experiences that foster effective and safe use. We present six principles for the design of generative AI applications that address unique characteristics of generative AI UX and offer new interpretations and extensions of known issues in the design of AI applications. Each principle is coupled with a set of design strategies for implementing that principle via UX capabilities or through the design process. The principles and strategies were developed through an iterative process involving literature review, feedback from design practitioners, validation against real-world generative AI applications, and incorporation into the design process of two generative AI applications. We anticipate the principles to usefully inform the design of generative AI applications by driving actionable design recommendations.

著者
Justin D.. Weisz
IBM Research AI, Yorktown Heights, New York, United States
Jessica He
IBM Research, Yorktown Heights, New York, United States
Michael Muller
IBM Research, Cambridge, Massachusetts, United States
Gabriela Hoefer
IBM, New York, New York, United States
Rachel Miles
IBM Software, San Jose, California, United States
Werner Geyer
IBM Research, Cambridge, Massachusetts, United States
論文URL

https://doi.org/10.1145/3613904.3642466

動画
User Experience Design Professionals’ Perceptions of Generative Artificial Intelligence
要旨

Among creative professionals, Generative Artificial Intelligence (GenAI) has sparked excitement over its capabilities and fear over unanticipated consequences. How does GenAI impact User Experience Design (UXD) practice, and are fears warranted? We interviewed 20 UX Designers, with diverse experience and across companies (startups to large enterprises). We probed them to characterize their practices, and sample their attitudes, concerns, and expectations. We found that experienced designers are confident in their originality, creativity, and empathic skills, and find GenAI’s role as assistive. They emphasized the unique human factors of “enjoyment” and “agency”, where humans remain the arbiters of “AI alignment”. However, skill degradation, job replacement, and creativity exhaustion can adversely impact junior designers. We discuss implications for human-GenAI collaboration, specifically copyright and ownership, human creativity and agency, and AI literacy and access. Through the lens of responsible and participatory AI, we contribute a deeper understanding of GenAI fears and opportunities for UXD.

著者
Jie Li
EPAM, Hoofddorp, Netherlands
Hancheng Cao
Stanford University, Stanford, California, United States
Laura Lin
Google, Mountain View, California, United States
Youyang Hou
Notion Labs, San Francisco, California, United States
Ruihao Zhu
Cornell University, Ithaca, New York, United States
Abdallah El Ali
Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands
論文URL

https://doi.org/10.1145/3613904.3642114

動画