[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-650695-105":59,"doc-detail-650695-en":134},{"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":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","conversion-of-2d-blueprints-into-3d-models-paper","Conversion of 2D Blueprints into 3D Models - Paper","","A method converts 2D blueprints into 3D models for deformable object categories from raw single-view images without external supervision. It uses an autoencoder that decomposes each image into four components: depth, color correction, viewpoint, and illumination, while avoiding explicit labels. Symmetry is used as a geometric cue, and partial symmetry is handled by a learned symmetry probability map integrated end-to-end. Experiments show unsupervised 3D reconstruction accuracy surpasses a supervised 2D correspondence baseline, supporting unsupervised 3D object learning for computer vision and graphics.",{"@graph":69,"@context":126},[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/conversion-of-2d-blueprints-into-3d-models-paper/650695/",{"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/conversion-of-2d-blueprints-into-3d-models-paper/650695.png","ImageObject",300,407,{"name":92,"@type":93},"PakDamar76","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-24",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What is the core objective of the proposed work?","Question",{"text":112,"@type":113},"To convert 2D blueprints/images into 3D models for deformable object categories by estimating 3D shape from single-view inputs.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Does the method require labeled ground truth or external supervision?",{"text":117,"@type":113},"No. It performs the decomposition and 3D recovery entirely without external supervision or explicit labels.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the approach deal with object symmetry and partial asymmetry?",{"text":121,"@type":113},"It uses symmetry as a geometric cue and introduces a learned symmetry probability map to handle cases where objects are not fully symmetric in shape or appearance.",{"name":123,"@type":110,"acceptedAnswer":124},"How does the proposed method perform compared with a supervised baseline?",{"text":125,"@type":113},"Experimental results indicate the unsupervised approach significantly outperforms a supervised method that relies on 2D image correspondences.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},650695,1792839440,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":29,"language":143,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":144,"faqs":145,"seo_title":146,"seo_description":67,"update_tm":133,"read_time":147},962090893057,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Conversion of 2D Blueprints into 3D Models  \nDr. Nasreen Fathima1, Mohammed Shezan2, Niha Rehaman3, Preksha Jain M4, Shishira N5 1Associate Professor & Head, Department of Computer Science and Design ATME College of  \nEngineering, Mysore, India  \n2,3,4,5 Department of Computer Science and Design Student of ATME College of Engineering, Mysore,  \nIndia  \nAbstract: We propose a method converting to 2D blueprints to 3D models the deformable object categories from raw single- view images, entirely without external supervision. Our approach leveragesan autoencoder framework that decomposes each input image into four fundamental components: depth, color correction, viewpoint, and illumination. This decomposition is achieved without explicit labels. We exploit the fact of converting object appearance, the underlying structure often remains symmetric, which can be used to guide the disentanglement process. To handle objects that may exhibit partial symmetry, we introduce a learned symmetry probability map, which is integrated into the model and learned end-to- end alongside the other components. Our method is capable of accurately recovering the 3D shape of various deformable objects, such as human faces, cat faces, and cars, from single-view images, without relying on any supervision or prior shape models. In experimental evaluations, we demonstrate that our unsupervised method significantly outperforms a supervised approach that relies on 2D image correspondences, achieving superior accuracy in 3D shape reconstruction. This work presents a promising step toward unsupervised 3D object learning, with potential applications in computer vision and graphics.  \nKeywords: Opencv, depth processing, Midas, image processing, pytorch.  \nI. INTRODUCTION  \nUnderstanding the 3D structure of images is crucial in many computer vision applications. While deep networks often interpret images as 2D textures, 3D modeling can better explain the variability inherent in natural images and potentially enhance overall image understanding. Motivated by this, we focus on the problem of learning 3D models fordeformable object categories. We study this problem under two challenging conditions. First, we assume that no 2D or 3D ground truth information—such as key points, segmentation, depth maps, or prior knowledge of 3D models—is available.  \nTraining without external supervision removes the need for manually collecting image annotations, which is a significant obstacle in applying deep learning to new domains. Second, our algorithm must operate on an unconstrained collection of single-view images, meaning it should not rely on multiple views of the same object instance. This is particularly important for deformable objects, where only single-view images are often available. Our learning algorithm takes a set of single-view images of a deformable object category and produces a deep network capable of estimating the 3D shape of any object instance from a single image. We frame this problem using an autoencoder that decomposes each image into four factors: albedo, depth, illumination, and viewpoint, without direct supervision for any of these factors. However, directly decomposing images into these components is ill-posed without additional assumptions. To minimize assumptions, we observe that many object categories are symmetric (e.g., animals and handcrafted objects) . If an object were perfectly symmetric, we could obtain a virtual second view by simply mirroring the image. In fact, stereo reconstruction could achieve 3D shape estimation if we had correspondences between these mirrored images. Motivated by this, we use symmetry as a geometric cue to help constrain the decomposition process. In practice, however, objects are rarely fully symmetric, either in shape or appearance. Variations in pose, expression, or other factors (e.g., hairstyle or facial features) result in non-symmetric shapes, and asymmetric textures or lighting conditions further complicate t","cbCaidVfGzZSSIdL","https://ap.wps.com/l/cbCaidVfGzZSSIdL","pdf",244911,"English","# I. INTRODUCTION\n# PROBLEM STATEMENT\n# EXISTING SYSTEM\n## a) AutoCAD and Revit","[{\"question\":\"What is the core objective of the proposed work?\",\"answer\":\"To convert 2D blueprints/images into 3D models for deformable object categories by estimating 3D shape from single-view inputs.\"},{\"question\":\"Does the method require labeled ground truth or external supervision?\",\"answer\":\"No. It performs the decomposition and 3D recovery entirely without external supervision or explicit labels.\"},{\"question\":\"How does the approach deal with object symmetry and partial asymmetry?\",\"answer\":\"It uses symmetry as a geometric cue and introduces a learned symmetry probability map to handle cases where objects are not fully symmetric in shape or appearance.\"},{\"question\":\"How does the proposed method perform compared with a supervised baseline?\",\"answer\":\"Experimental results indicate the unsupervised approach significantly outperforms a supervised method that relies on 2D image correspondences.\"}]","Conversion of 2D Blueprints into 3D Models - Paper | PDF",15]