arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.03330cs.HCcs.AIcs.CVcs.GR
收藏

ControlGUI: 通过感知视觉流引导生成GUI探索

ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow

Aalto University(阿尔托大学)

Aryan Garg, Yue Jiang, Antti Oulasvirta

AI总结:

本文提出ControlGUI,通过提示、草图和视觉流三种输入灵活控制生成过程,实现低效生成界面草图,快速探索大规模设计空间。

摘要:

在界面设计初期,设计师需要生成多个草图以探索设计空间,但现有工具无法有效支持此阶段,因为它们要求过多细节。尽管生成式AI的进展带来了希望,但实际应用中表达模糊想法仍具挑战性。本文提出基于扩散的低效生成方法,允许通过三种输入(提示、草图和视觉流)灵活控制生成过程。设计师可提供任意组合的输入,生成多样化的低保真解决方案。该方法的优势在于能以极低的输入规格快速探索大规模设计空间。我们展示了不同输入组合的定性结果,并证明模型更准确地符合这些规范。

英文摘要:

During the early stages of interface design, designers need to produce multiple sketches to explore a design space. Design tools often fail to support this critical stage, because they insist on specifying more details than necessary. Although recent advances in generative AI have raised hopes of solving this issue, in practice they fail because expressing loose ideas in a prompt is impractical. In this paper, we propose a diffusion-based approach to the low-effort generation of interface sketches. It breaks new ground by allowing flexible control of the generation process via three types of inputs: A) prompts, B) wireframes, and C) visual flows. The designer can provide any combination of these as input at any level of detail, and will get a diverse gallery of low-fidelity solutions in response. The unique benefit is that large design spaces can be explored rapidly with very little effort in input-specification. We present qualitative results for various combinations of input specifications. Additionally, we demonstrate that our model aligns more accurately with these specifications than other models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑