請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97553完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳彥仰 | zh_TW |
| dc.contributor.advisor | Mike Y. Chen | en |
| dc.contributor.author | 王舜昱 | zh_TW |
| dc.contributor.author | Shun-Yu Wang | en |
| dc.date.accessioned | 2025-07-02T16:26:05Z | - |
| dc.date.available | 2025-07-03 | - |
| dc.date.copyright | 2025-07-02 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-03-10 | - |
| dc.identifier.citation | [1] S. AI. Stable diffusion, 2022. Last accessed 18 June 2023.
[2] S. Amershi, D. Weld, M. Vorvoreanu, A. Fourney, B. Nushi, P. Collisson, J. Suh, S. Iqbal, P. N. Bennett, K. Inkpen, J. Teevan, R. Kikin-Gil, and E. Horvitz. Guidelines for human-AI interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, page 1–13, New York, NY, USA, May 2019. ACM. [3] Andrew. Stable diffusion prompt: a definitive guide, 2022. [4] A. Cantino. Prompt engineering tips and tricks with gpt-3. https://blog.andrewcantino.com/blog/2021/04/21/prompt-engineering-tips-and-tricks/, April 2021. Accessed: December 4, 2023. [5] S. Chaillou. Archigan: Artificial intelligence x architecture. In Architectural Intelligence: Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2019), pages 117–127, Singapore, 2020. Springer, Springer Nature Singapore. [6] G. Chen, G. Li, Y. Nie, C. Xian, and A. Mao. Stylistic indoor colour design via bayesian network. Computers & Graphics, 60:34–45, 2016. [7] K. Chen, K. Xu, Y. Yu, T.-Y. Wang, and S.-M. Hu. Magic decorator: automatic material suggestion for indoor digital scenes. ACM Transactions on graphics (TOG), 34(6):1–11, 2015. [8] F. Ching and C. Binggeli. Interior Design Illustrated. Wiley, New Jersey, US, 2012. [9] F. D. Ching. Architecture: Form, space, and order. John Wiley & Sons, New Jersey, US, 2023. [10] J. Y. Cho and J. Suh. Spatial color efficacy in perceived luxury and preference to stay: An eye-tracking study of retail interior environment. Frontiers in Psychology, 11:296, 2020. [11] J. J. Y. Chung and E. Adar. Artinter: Ai-powered boundary objects for commissioning visual arts. In Proceedings of the 2023 ACM Designing Interactive Systems Conference, DIS ’23, page 1997–2018, New York, NY, USA, 2023. Association for Computing Machinery. [12] S. Clemons and J. McLain-Kark. Computer–aided design in interior design programs: Status and challenges. Journal of Interior Design Education and Research, 17(2):47–50, 1991. [13] J. Cook. How to write effective prompts for chatgpt: 7 essential steps for best results. https://www.forbes.com/sites/jodiecook/2023/06/26/how-to-write-effective-prompts-for-chatgpt-7-essential-steps-for-best-results/?sh=3f4e57832a18, June 2023. Accessed: December 4, 2023. [14] H. Dang, L. Mecke, F. Lehmann, S. Goller, and D. Buschek. How to prompt? Opportunities and challenges of zero- and few-shot learning for human-ai interaction in creative applications of generative models, 2022. [15] C. DESIGN. How long does an interior design project take?, 2023. [16] G. E, C. D. Schunn, A. R. Silva, T. L. Bauer, G. W. Crabtree, C. M. Johnson, T. Odomosu, S. T. Picraux, R. K. Sawyer, R. P. Schneider, et al. The art of research: A divergent/convergent thinking framework and opportunities for science-based approaches. Engineering a Better Future: Interplay between Engineering, Social Sciences, and Innovation, 66(12):167–186, 2018. [17] GPTBOT.io. Mastering chatgpt: How to craft effective prompts (full guide). https://gptbot.io/master-chatgpt-prompting-techniques-guide/, March 2023. Accessed: December 4, 2023. [18] Y. Hao, Z. Chi, L. Dong, and F. Wei. Optimizing prompts for text-to-image generation, 2022. [19] I. E. Harel and S. E. Papert. Constructionism. Ablex Publishing, 123, 1991. [20] R. Imamguluyev. Application of fuzzy logic model for correct lighting in computer aided interior design areas. In Intelligent and Fuzzy Techniques: Smart and Innovative Solutions: Proceedings of the INFUS 2020 Conference, Istanbul, Turkey, July 21-23, 2020, pages 1644–1651, Cham, 2021. Springer, Springer International Publishing. [21] O. S. Islamoglu and K. O. Deger. The location of computer aided drawing and hand drawing on design and presentation in the interior design education. Procedia-Social and Behavioral Sciences, 182:607–612, 2015. [22] S. F. Javaid and J. P. Pandarakalam. The association of creativity with divergent and convergent thinking. Psychiatria danubina, 33(2):133–139, 2021. [23] A. L. Khoroshko et al. The research of the possibilities and application of the autocad software package for creating electronic versions of textbooks for “engineering and computer graphics” course. TEM Journal, 9(3):1141–1149, 2020. [24] K. H. Kim and R. A. Pierce. Convergent Versus Divergent Thinking, pages 245–250. Springer New York, New York, NY, 2013. [25] V. Liu and L. B. Chilton. Design guidelines for prompt engineering text-to-image generative models. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, CHI ’22, New York, NY, USA, 2022. Association for Computing Machinery. [26] W. Ma, X. Wang, J. Wang, X. Xiang, and J. Sun. Generative design in building information modelling (BIM): approaches and requirements. Sensors, 21(16):5439, 2021. [27] mordorintelligence. Interior design industry size & share analysis - growth trends & forecasts (2023 - 2028), 2023. [28] J. I. of Fashion Technology. Interior design process–how long does it take?, 2023. [29] A. Ogino. A design support system for indoor design with originality suitable for interior style. In 2017 International Conference on Biometrics and Kansei Engineering (ICBAKE), pages 74–79, Kyoto, Japan, 2017. IEEE, IEEE. [30] B. H. Park and K. H. Hyun. Analysis of pairings of colors and materials of furnishings in interior design with a data-driven framework. Journal of Computational Design and Engineering, 9(6):2419–2438, 2022. [31] J. Pejic and P. Pejic. Linear kitchen layout design via machine learning. AI EDAM, 36:e9, 2022. [32] H. PRO. Free template: Interior design schedule & guide, 2023. [33] H. PRO. How many hours do interior designers work?, 2023. [34] S. Ramlochan. Enhancing stable diffusion models with controlnet. https://promptengineering.org/enhancing-stable-diffusion-models-with-control-nets/, March 2023. Accessed December 5, 2023. [35] R. G. G. Rohit Ramesh. Controlnet - adding control to stable diffusion’s image generation. https://blog.segmind.com/what-is-stable-diffusion-controlnet/, October 2023. Accessed December 5, 2023. [36] Y. Shu. Application of computer aided design software in interior design. In Journal of Physics: Conference Series, page 022035, Bristol, BS2 OGR, UK, 2021. IOP Publishing, IOP Publishing. [37] N. Sitanggang, P. L. A. Luthan, and F. A. Dwiyanto. The effect of google sketchup and need for achievement on the students’ learning achievement of building interior design. Int. J. Emerg. Technol. Learn., 15:4–19, 2020. [38] C. Spence. Senses of place: architectural design for the multisensory mind. In Cognitive Research: Principles and Implications, New York, NY, US, September 2020. Springer Science and Business Media LLC. [39] Steins. Stable diffusion —controlnet clearly explained! https://medium.com/@steinsfu/stable-diffusion-controlnet-clearly-explained-f86092b62c89, June 2023. Accessed: December 5, 2023. [40] L. Todd. Creativity and convergent thinking: Reflections, connections and practical considerations. 123, 54(12):245–250, 2016. [41] N. Umezu and E. Takahashi. Visualizing color term differences based on images from the web. Journal of Computational Design and Engineering, 4(1):37–45, 2017. [42] D. Wang, E. Churchill, P. Maes, X. Fan, B. Shneiderman, Y. Shi, and Q. Wang. From human-human collaboration to human-ai collaboration: Designing ai systems that can work together with people. In CHI EA ’20: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, pages 1–6, New York, NY, USA, April 2020. Association for Computing Machinery. [43] S.-Y. Wang, W.-C. Su, S. Chen, C.-Y. Tsai, M. Misztal, K. M. Cheng, A. Lin, Y. Chen, and M. Y. Chen. Roomdreaming: Generative-ai approach to facilitating iterative, preliminary interior design exploration. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI ’24, New York, NY, USA, 2024. Association for Computing Machinery. [44] L. K. Waxman and H. Zhang. Computer aided design training methods in interior design professional practice. Journal of Interior Design, 21(1):21–29, 1995. [45] T. Weiss, I. Yildiz, N. Agarwal, E. Ataer-Cansizoglu, and J.-W. Choi. Image-driven furniture style for interactive 3d scene modeling. In Computer Graphics Forum, pages 57–68, Hoboken, New Jersey, US, 2020. Wiley Online Library. [46] Wiskkey. The maximum usable length of a stable diffusion text prompt, 2022. [47] T. Xiao, Y. Liu, B. Zhou, Y. Jiang, and J. Sun. Unified perceptual parsing for scene understanding, 2018. [48] F. Yu, B. Liang, B. Tang, and H. Wu. An interactive differential evolution algorithm based on backtracking strategy applied in interior layout design. Algorithms, 16(6):275, 2023. [49] L. Zaman, W. Stuerzlinger, C. Neugebauer, R. Woodbury, M. Elkhaldi, N. Shireen, and M. Terry. Gem-ni: A system for creating and managing alternatives in generative design. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, CHI ’15, page 1201–1210, New York, NY, USA, 2015. Association for Computing Machinery. [50] J. Zamfirescu-Pereira, R. Y. Wong, B. Hartmann, and Q. Yang. Why johnny can’t prompt: How non-ai experts try (and fail) to design llm prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, CHI ’23, New York, NY, USA, 2023. Association for Computing Machinery. [51] L. Zhang, A. Rao, and M. Agrawala. Adding conditional control to text-to-image diffusion models, 2023. [52] J. Zhu, Y. Guo, and H. Ma. A data-driven approach for furniture and indoor scene colorization. IEEE transactions on visualization and computer graphics, 24(9):2473–2486, 2017. [53] W. Zhu, S. Shang, W. Jiang, M. Pei, and Y. Su. Convergent thinking moderates the relationship between divergent thinking and scientific creativity. Creativity Research Journal, 31(3):320–328, 2019. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97553 | - |
| dc.description.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。 | zh_TW |
| dc.description.abstract | 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. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-02T16:26:05Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-02T16:26:05Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 ii
摘要 iv Abstract v Contents vi List of Figures ix List of Tables xiii 1 Introduction 1 2 Related Work 6 2.1 Generative-AI Interior Design Tools . . . . . . . . . . . . . . . . . . . . 6 2.2 Computer Aided Design (CAD) Tools for Interior Design Exploration . . 7 2.3 Generative Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3 STUDY #1: Formative Study 10 3.1 Study Design, Procedure, and Participants . . . . . . . . . . . . . . . . . 10 3.2 Findings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 4 System Design and Implementation 14 4.1 Web-based User Interface . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.2 Generating Designs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.2.1 Understanding Room Elements and Spatial Information . . . . . 16 4.2.2 Generating Designs based on the Room . . . . . . . . . . . . . . 17 4.2.3 Image Generation Latency . . . . . . . . . . . . . . . . . . . . . 18 4.2.4 Expanding Breadth of Exploration . . . . . . . . . . . . . . . . . 18 4.2.5 Supporting Depth of Exploration . . . . . . . . . . . . . . . . . . 19 5 STUDY #2: Quality Assessment of AI-generated Interior Designs 20 5.1 Assessment by Interior Designers . . . . . . . . . . . . . . . . . . . . . 21 5.1.1 Participants and Procedure . . . . . . . . . . . . . . . . . . . . . 22 5.2 Results and Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 6 STUDY #3: Self-Guided Design Exploration by Owners 24 6.1 Study Design and Procedure . . . . . . . . . . . . . . . . . . . . . . . . 24 6.2 Participants . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 6.3 Results: RoomDreaming vs. Existing Tools . . . . . . . . . . . . . . . . 25 6.3.1 Breadth and Depth of Exploration . . . . . . . . . . . . . . . . . 25 6.3.2 Overall Efficiency and Satisfaction . . . . . . . . . . . . . . . . 27 6.4 Results: RoomDreaming vs. Generative-AI . . . . . . . . . . . . . . . . 28 6.4.1 Breadth and Depth of Exploration . . . . . . . . . . . . . . . . . 28 6.4.2 Overall Efficiency and Satisfaction . . . . . . . . . . . . . . . . 29 7 STUDY #4: System Improvement 31 7.1 Feedback and RoomDreaming V2 Improvements . . . . . . . . . . . . . 31 7.1.1 Generated designs being too similar to Likes and Bookmarks . . . 32 7.1.2 Lack of support for negative user requirements . . . . . . . . . . 32 7.1.3 Long batch generation time . . . . . . . . . . . . . . . . . . . . 32 8 STUDY #5: Owner-Designer Co-design Exploration 33 8.1 Study Design and Procedure . . . . . . . . . . . . . . . . . . . . . . . . 33 8.2 Participants . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 8.3 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 8.3.1 Identification of Owners’ Needs. . . . . . . . . . . . . . . . . . . 35 8.3.2 Design Alternative Assessment with Owners. . . . . . . . . . . . 36 8.3.3 Estimation of Time Saved. . . . . . . . . . . . . . . . . . . . . . 36 9 Discussion, Limitations, and Future Work 37 9.1 Designing for Human + AI . . . . . . . . . . . . . . . . . . . . . . . . . 37 9.2 Tailoring to Region-specific Preferences . . . . . . . . . . . . . . . . . . 38 9.3 Creativity Control . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 9.4 Element-specific Preference and Generation . . . . . . . . . . . . . . . . 39 9.5 Spatial Rationality and Multi-room Support . . . . . . . . . . . . . . . . 39 10 Conclusion 40 Bibliography 41 | - |
| dc.language.iso | en | - |
| dc.subject | 人本人工智慧 | zh_TW |
| dc.subject | 建築 | zh_TW |
| dc.subject | 室內設計 | zh_TW |
| dc.subject | 生成式人工智慧 | zh_TW |
| dc.subject | human-centered AI | en |
| dc.subject | Generative-AI | en |
| dc.subject | interior design | en |
| dc.subject | architecture | en |
| dc.title | 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 | zh_TW |
| dc.title | RoomDreaming: Generative-AI Approach to Facilitating Iterative, Preliminary Interior Design Exploration | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 蔡欣叡;鄭龍磻;余能豪 | zh_TW |
| dc.contributor.oralexamcommittee | Hsin-Ruey Tsai;Lung-Pan Cheng;Neng-Hao Yu | en |
| dc.subject.keyword | 生成式人工智慧,室內設計,建築,人本人工智慧, | zh_TW |
| dc.subject.keyword | Generative-AI,interior design,architecture,human-centered AI, | en |
| dc.relation.page | 50 | - |
| dc.identifier.doi | 10.6342/NTU202500761 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-03-11 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | - |
| dc.date.embargo-lift | 2025-07-03 | - |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf | 23.65 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。