探討利用生成式人工智慧輔助室內設計前期流程之探索設計

Abstract

室內設計旨在創造建築空間內美觀且功能性的環境。對於一個簡單的房間，初步設計探索，目前需要多次會議和多天的工作，才能讓室內設計師通過佈局、家具、形式、顏色和材料來融入房主的個人偏好。我們提出了 RoomDreaming，一種基於生成式 AI 的方法，旨在促進初步的室內設計探索。使屋主和設計師能夠快速、高效地迭代各種 AI 生成的室內設計方案，每個方案都獨特地契合實際空間佈局和個人設計偏好。我們進行了一系列前測和總結的研究，共有 18 位屋主和 20 位室內設計師參與，以幫助設計、改進和評估 RoomDreaming。屋主稱，RoomDreaming 有效地增加了設計探索的廣度和深度，提高了效率和滿意度。設計師稱，與 RoomDreaming 進行一小時的協作設計所產生的結果相當於傳統屋主-設計師會議的幾天成果，以及設計師需要數天到數週的設計開發和完善工作。

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.