Table of Contents
Fetching ...

Breaking the Midas Spell:Understanding Progressive Novice-AI Collaboration in Spatial Design

Zijun Wan, Jiawei Tang, Linghang Cai, Xin Tong, Can Liu

TL;DR

This research conducted a Wizard-of-Oz study, where Novices and AI worked together to finish spatial design tasks using various AI models, leading to the understanding of the opportunities and challenges in the human-AI co-creation process.

Abstract

In spatial design, Artificial Intelligence (AI) tools often generate the entire spatial design outcome in a single automated step, rather than engaging users in a deepening and iterative process. This significantly reduces users' involvement, learning, and creative capabilities, leading to a superficial understanding of spatial design. We conducted a Wizard-of-Oz study, where Novices and AI (acted by experimenters) worked together to finish spatial design tasks using various AI models. We identified typical function and workflow patterns adopted by the participants, leading to the understanding of the opportunities and challenges in the human-AI co-creation process. Based on insights gathered from this research, we proposed some design implications of the novice-AI collaboration system that aims to democratize spatial design through a progressive, iterative co-creation process.

Breaking the Midas Spell:Understanding Progressive Novice-AI Collaboration in Spatial Design

TL;DR

This research conducted a Wizard-of-Oz study, where Novices and AI worked together to finish spatial design tasks using various AI models, leading to the understanding of the opportunities and challenges in the human-AI co-creation process.

Abstract

In spatial design, Artificial Intelligence (AI) tools often generate the entire spatial design outcome in a single automated step, rather than engaging users in a deepening and iterative process. This significantly reduces users' involvement, learning, and creative capabilities, leading to a superficial understanding of spatial design. We conducted a Wizard-of-Oz study, where Novices and AI (acted by experimenters) worked together to finish spatial design tasks using various AI models. We identified typical function and workflow patterns adopted by the participants, leading to the understanding of the opportunities and challenges in the human-AI co-creation process. Based on insights gathered from this research, we proposed some design implications of the novice-AI collaboration system that aims to democratize spatial design through a progressive, iterative co-creation process.

Paper Structure

This paper contains 29 sections, 5 figures, 2 tables.

Figures (5)

  • Figure 1: (1) The first pilot study with a simple sticky-note format; (2) 12 (3*3 + 1 + 2) functional card examples in the second pilot study, for example, T-I means Text to Image
  • Figure 2: The formal Experiment Process: (a) the entire collaboration workflow; (b) the "front-end" operations in Spline and Cardbox, where participants can call AI for help when they are modelling in the Spline. Each call consumes one specific function card; (c) the operations in the "back-end", where wizards act as AI, give output to participants through multiple AI tools
  • Figure 3: the Common Workflow: Ideation - Lo-fi design - Review - Hi-fi design
  • Figure 4: Specific workflow examples that have multiple differences compared with the common workflow: P1 jumped some steps; P4 seperated the generation of space and individual models; p7 generated models from an isometric view without using traditional layout plan; p12 is considered highly innovative by using style transfer to unify the visual styles without using spatial layout
  • Figure 5: (A) the Main interface with multiple tools and the information panel; (B) Floating AI Spirit with three states: B’, B’’, B’’’