[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-663923-105":59,"doc-detail-663923-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","utilization-of-image-generating-ai-in-the-architectural-design-process-focusing-on-the-comprehension-and-expressiveness-of-sketch-to-image-input-based-image-generating-ai","Utilization of Image-generating AI in the Architectural Design Process - Focusing on the Comprehension and Expressiveness of Sketch-to-image Input-based Image-generating AI","","Study examines how image-generating AI supports architectural design when driven by hand-drawn sketches. Five sketch-to-image web tools—fabrie, LookX AI, PromeAI, mnml.ai, and Rerender AI—are assessed for comprehension and expressiveness. Architectural experts identify key features visible in sketches, then expert perceptions are compared with AI outputs to judge spatial interpretation, material depiction, and awareness of spatial context. Results show differing strengths, with proposals for integrating AI visualization with sensor feedback loops and material-aware simulation to improve early-stage design ideation, evaluation, and automation.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/utilization-of-image-generating-ai-in-the-architectural-design-process-focusing-on-the-comprehension-and-expressiveness-of-sketch-to-image-input-based-image-generating-ai/663923/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/utilization-of-image-generating-ai-in-the-architectural-design-process-focusing-on-the-comprehension-and-expressiveness-of-sketch-to-image-input-based-image-generating-ai/663923.png","ImageObject",300,407,{"name":92,"@type":93},"Guten tag","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-29",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Which sketch-to-image AI tools are evaluated in the study?","Question",{"text":112,"@type":113},"The study analyzes five tools: fabrie, LookX AI, PromeAI, mnml.ai, and Rerender AI.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the study measure AI performance in architectural design contexts?",{"text":117,"@type":113},"Architectural experts identify key architectural features in sketches, and those insights are compared against AI-generated outputs to evaluate accuracy in spatial perception, material representation, and contextual awareness.",{"name":119,"@type":110,"acceptedAnswer":120},"What is the reported value of integrating AI-generated imagery with sensor feedback loops?",{"text":121,"@type":113},"Combining AI visualization with sensor-informed environmental data and performance metrics helps architects evaluate spatial quality and environmental responsiveness earlier in the design process, supporting rapid ideation and iterative improvement.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},663923,1793234234,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":26},687212321768,"https://ap-avatar.wpscdn.com/avatar/a0010bdbe886d2fe77?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789897067658708522","Sensors and Materials, Vol. 37, No. 6 (2025) 2607–2629 2607  \nMYU Tokyo  \nS & M 4077  \nUtilization of Image-generating AI in the Architectural Design Process: Focusing on the Comprehension and Expressiveness of ‘Sketch-to-image’ Input-based Image-generating AI  \nHan Yeol Baek 1 and Jung Hoon Kim2*  \n1Department of Architecture, Hannam University, Daejeon 34430, Korea  \n2Department of Urban Planning and Real Estate Studies, Pyeongtaek University, Gyeonggi-Do 17869, Korea  \n(Received February 3, 2025; accepted June 13, 2025)  \nKeywords: image-generating AI, sketch-to-image tool, AI-based visualization, generative AI in architecture, architectural design  \nIn this study, we explore the role of image-generating AI in architectural design, focusing on sketch-to-image AI tools and their ability to interpret hand-drawn sketches. Five AI tools, namely, fabrie, LookX AI, PromeAI, [mnml.ai](mnml.ai), and Rerender AI, were analyzed for their comprehension and expressiveness in architectural contexts. To evaluate the effectiveness of these AI tools, architectural experts were surveyed to identify key architectural features present in sketches. These expert insights were then compared with AI-generated outputs to assess their accuracy in spatial perception, material expression, and spatial context awareness. Fabrie excelled in spatial interpretation and material representation, efficiently converting conceptual sketches into detailed visualizations. PromeAI demonstrated strong creative flexibility, supporting iterative design processes with diverse customization options. However, some contextual inconsistencies and missing environmental elements were noted. Importantly, in this study, we discuss how AI-generated imagery can be integrated with sensor-based feedback loopsand material-aware simulation tools to enhance the design process. By combining AI visualization with sensor-informed environmental data and performance metrics, architects canmore effectively evaluate spatial quality and environmental responsiveness in early-stage design. The study highlights AI’s potential as a complementary tool in early-stage design, enhancing rapid ideation, visualization, and design automation. By integrating AI into workflows, architects can expand creativity and efficiency while exploring a wider range of design possibilities. Furthermore, advancements in AI learning models, prompt engineering, and collaborative design processes particularly those that incorporate sensor-derived data are emphasized to strengthen AI’s role in bridging digital tools with human-driven creativity in architectural practice.  \n* Corresponding author: [e-mail:](e-mail: urban@ptu.ac.kr)[ ](e-mail: urban@ptu.ac.kr)[urban@ptu.ac.kr](e-mail: urban@ptu.ac.kr)[ ](e-mail: urban@ptu.ac.kr)[https://doi.org/10.18494/SAM5592](https://doi.org/10.18494/SAM5592)  \nISSN 0914-4935 © MYU K.K.  \n[https://myukk.org/](https://myukk.org/)  \n1. Introduction  \n1.1 Background and objectives  \nIn 2022, the artwork Theatre D’opera Spatial, created using the image-generating AIMidJourney, won the grand prize at the Colorado State Fair Fine Arts Competition, sparking widespread controversy.(1,2) Additionally, in 2024, OpenAI, a leading AI company, introduced Sora, an AI designed for video production. Its realistic and expressive results became a global topic of discussion.(3) AI, by leveraging vast datasets and computational processes, generates novel outputs in a fraction of the time it would take a human.(4) Given that both AI and humans engage in creative processes by building on existing knowledge, it is increasingly challenging to draw a clear boundary between the two.(5)  \nMidJourney, a prominent example of image-generating AI, is renowned for its ability to produce creative and artistic images. The platform generates images on the basis of textual prompts, allowing the AI to interpret the user’s intent and produce related imagery.(6) Such applications of image-generating AI have transcended tra","cbCaicsLZOrpP5gZ","https://ap.wps.com/l/cbCaicsLZOrpP5gZ","pdf",2041200,24,"English","# 1. Introduction\n## 1.1 Background and objectives\n## 1.2 Research methods and scope","[{\"question\":\"Which sketch-to-image AI tools are evaluated in the study?\",\"answer\":\"The study analyzes five tools: fabrie, LookX AI, PromeAI, mnml.ai, and Rerender AI.\"},{\"question\":\"How does the study measure AI performance in architectural design contexts?\",\"answer\":\"Architectural experts identify key architectural features in sketches, and those insights are compared against AI-generated outputs to evaluate accuracy in spatial perception, material representation, and contextual awareness.\"},{\"question\":\"What is the reported value of integrating AI-generated imagery with sensor feedback loops?\",\"answer\":\"Combining AI visualization with sensor-informed environmental data and performance metrics helps architects evaluate spatial quality and environmental responsiveness earlier in the design process, supporting rapid ideation and iterative improvement.\"}]","Utilization of Image-generating AI in the Architectural Design Process - Focusing on the Comprehension and Expressiveness of Sketch-to-image Input-based Image-generating AI | PDF"]