arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2608.28001cs.HCcs.MA

FocusGen:通过模拟角色智能体的虚拟焦点小组拓展视觉设计探索

FocusGen: Expanding Visual Design Exploration with a Simulated Focus Group of Persona Agents

Jaewon Choi, Helena Vasconcelos, Hyun Lee, Carolyn Zou, Tak Yeon Lee, Michael Bernstein

AI总结:

FocusGen是引入虚拟角色智能体焦点小组的交互式视觉设计系统,可拓展设计探索、提升输出多样性,助力设计师突破思维定式,同时存在刻板印象风险,为早期构思提供发散支架。

AI中文摘要:

创意专业人士很少为自己设计,而是为需要预判偏好的受众设计。然而当前的文生图探索工具完全依赖设计师自身的输入来产生多样性——包括他们的提示词、选定的维度、搜索查询等——将探索局限于设计师已知的寻找范围内。我们提出FocusGen,这是一个交互式系统,通过由模拟角色智能体构成的“虚拟焦点小组”将外部视角引入视觉设计探索。与之前多智能体作为评论者收敛于单一迭代作品的角色系统不同,FocusGen将角色用作并行生成器:每个智能体由人口统计数据、程序生成的背景故事以及通过访谈得出的审美偏好构建而成,独立驱动迭代生成循环以产生自身的视觉概念,将单一设计 brief 转化为一系列受受众条件约束的方向。我们通过真人参与者确认,迭代优化循环产生的输出比零样本生成更受人们偏好;通过大规模合成智能体表明,角色条件化比通用助手基线产生更高的视觉多样性(由CLIP距离衡量并经人类感知判断证实),且开放式偏好访谈比结构化访谈为人类和合成群体带来更多样的输出,同时发现智能体群体仅能恢复可比人类群体多样性的一部分。对16名创意专业人士的定性研究显示,FocusGen帮助设计师发现未预料到的方向、克服思维定式、探究受众情境,同时暴露了我们分析的刻板印象风险。我们将FocusGen定位为早期构思的发散支架,而非受众研究的替代品。

英文摘要:

Creative professionals rarely design for themselves--they design for audiences whose preferences they must anticipate. Yet current text-to-image exploration tools derive diversity entirely from the designer's own input--their prompts, their chosen dimensions, their search queries--confining exploration to what the designer already knows to look for. We present FocusGen, an interactive system that introduces external perspectives into visual design exploration through a "virtual focus group" of simulated persona agents. In contrast to prior persona systems in which multiple agents converge as critics on a single evolving artifact, FocusGen uses personas as parallel generators: each agent--constructed from demographic data, a procedurally generated backstory, and aesthetic preferences elicited through interviews--independently drives an iterative generation loop that produces its own visual concept, transforming one design brief into a spectrum of audience-conditioned directions. With real human participants, we confirm that the iterative refinement loop produces outputs people prefer over zero-shot generation. With synthetic agents at scale, we show that persona conditioning yields higher visual diversity than a generic-assistant baseline--measured by CLIP distance and corroborated by human perceptual judgments--and that open-ended preference interviews yield more diverse outputs than structured ones for both human and synthetic cohorts, while also revealing that agent cohorts recover only part of the diversity of comparable human cohorts. A qualitative study with 16 creative professionals suggests FocusGen helps designers discover unanticipated directions, overcome fixation, and probe audience contexts--while surfacing stereotyping risks that we analyze. We position FocusGen as a divergence scaffold for early-stage ideation rather than a substitute for audience research.

补充信息

↑