[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-650859-105":59,"doc-detail-650859-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","from-architectural-sketch-to-conceptual-representation-using-structure-aware-diffusion-model-to-generate-renderings-of-school-buildings","From Architectural Sketch to Conceptual Representation - Using structure-aware diffusion model to generate renderings of school buildings","","Generative artificial intelligence accelerates architectural communication by enabling renderings from sketches, but existing text-to-image generation often misses structural details emphasized by architects. In school building design, controlling components such as windows and doors—shape, proportion, and placement—is essential for accurately reflecting design intentions. The work proposes a structure-aware diffusion model that refines sketch guidance via retrieval augmentation using architectural component information. Experiments show improved detail fidelity and realism in generated school building images aligned with traditional architectural designs.",{"@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/from-architectural-sketch-to-conceptual-representation-using-structure-aware-diffusion-model-to-generate-renderings-of-school-buildings/650859/",{"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/from-architectural-sketch-to-conceptual-representation-using-structure-aware-diffusion-model-to-generate-renderings-of-school-buildings/650859.png","ImageObject",300,407,{"name":92,"@type":93},"Bulrr","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-24",true,{"@type":102,"interactionType":103,"userInteractionCount":81},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why do current text-to-image models struggle for architectural rendering of school buildings?","Question",{"text":112,"@type":113},"Text prompts often cannot precisely control structural details such as window placements, floor counts, and proportional relationships between components. This limits accuracy and clarity when conveying architects' design intentions.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What problem does the proposed method address?",{"text":117,"@type":113},"It addresses missing or simplified architectural component details in generated images derived from sketches, especially for windows and doors in school buildings.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the structure-aware diffusion model improve generation quality?",{"text":121,"@type":113},"The method extracts architectural component regions, retrieves matching components from an architectural component dataset, integrates them into sketches, and then uses the refined sketches with text prompts to generate detailed, realistic school building renderings.","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},650859,1792848471,{"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":81,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143},5909892115043,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","From Architectural Sketch to Conceptual Representation  \nUsing structure-aware diffusion model to generate renderings of school buildings  \nZhengyang Wang 1, Hao Jin 1, Xusheng Du 1, Yuxiao Ren2, Ye Zhang2 and Haoran Xie1  \n1Japan Advanced Institute of Science and Technology  \n2Tianjin University  \n[1](1s2310021@jaist.ac.jp)[s2310021@jaist.ac.jp](1s2310021@jaist.ac.jp), ORCID: 0009-0008-6600-6911  \nAbstract. Generative Artificial Intelligence (AI) has advanced rapidly, enabling the generation of renderings from architectural sketches. This progress has significantly improved the efficiency of communication and conceptual expression during the early stage of architectural design. However, generated images often lack the structural details from architects' sketches. While sketches typically emphasize the overall structure, crucial components such as windows and doors are often represented by simple lines or omitted entirely. For school buildings, it is essential to control architectural components, such as the shape and proportion of windows, as these factors directly influence the accuracy of the generated images in reflecting the architect's design intentions. To address this issue, we propose a structure-aware diffusion model for architectural image generation to refine expressing design intentions through retrieval augmentation. Our framework utilizes architectural components to enhance the generation process, addressing the details that may be lacking in the sketches. These components provide clear spatial and structural details, improving the model's ability to interpret and generate architectural details. The refined sketches, combined with text prompts, are fed into the proposed structure-aware diffusion model to generate detailed and realistic school building images. The experiment results demonstrate the effectiveness of our framework in generating architectural designs.  \nKeywords. Architectural Image Generation, Diffusion Model, Sketchguided, Retrieval-augmented Generation, Architectural Components  \n1. Introduction  \nDuring the early stages of architectural design, designers frequently engage in the iterative process of creating renderings to communicate design concepts and architectural intentions to stakeholders. Compared to the traditional tools such as Sketchup, Rhino and ArcGIS, image generation models like Midjourney can significantly reduce the time and effort required for image production, making the  \n–LEAVE THIS WHITE BOX ON PAGE 01!!–If it has moved, you can cut and paste it back to page 1, right click on the boundary and choose 'More Layout Options...' and then under 'Vertical', choose 'Absolute position' -24 cm (below Page).  \nZ. WANG ET AL.  \nprocess more efficient (Li et al., 2024). However, the current text-to-image generation models face challenges in controlling the structure of buildings in image generation. Text prompts alone often fail to convey specific details such as window placements, floor counts, or proportional relationships between structural architectural components.  \nIn this work, we especially focus on school buildings, which are architectural structures with typically featured designs and detailed architectural characteristics. Generating images of school buildings through text-to-image models remains a challenge (Paananen et al., 2024), as the text input may have difficulty controlling the details of the building. This limitation impedes architects in effectively communicating their design intentions, reducing the clarity and precision of the architectural concept presented to clients and stakeholders. Meanwhile, for school buildings, the window-towall ratio can significantly influence factors such as natural lighting, energy efficiency, and the attention levels of students, making precise architectural detailing even more critical (Heschong et al., 2002). To address this issue, we adopt sketches as an additional condition, providing structural foundation information such as the ov","cbCaivMRCYNOIxyz","https://ap.wps.com/l/cbCaivMRCYNOIxyz","pdf",1666832,"English","# Introduction\n# Related Works\n## Diffusion Model","[{\"question\":\"Why do current text-to-image models struggle for architectural rendering of school buildings?\",\"answer\":\"Text prompts often cannot precisely control structural details such as window placements, floor counts, and proportional relationships between components. This limits accuracy and clarity when conveying architects' design intentions.\"},{\"question\":\"What problem does the proposed method address?\",\"answer\":\"It addresses missing or simplified architectural component details in generated images derived from sketches, especially for windows and doors in school buildings.\"},{\"question\":\"How does the structure-aware diffusion model improve generation quality?\",\"answer\":\"The method extracts architectural component regions, retrieves matching components from an architectural component dataset, integrates them into sketches, and then uses the refined sketches with text prompts to generate detailed, realistic school building renderings.\"}]","From Architectural Sketch to Conceptual Representation - Using structure-aware diffusion model to generate renderings of school buildings | PDF",25]