[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-649784-105":59,"doc-detail-649784-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","2d-cross-view-object-segmentation-and-perceptual-grouping-in-computer-aided-design-drawings","2D Cross-View Object Segmentation and Perceptual Grouping in Computer-Aided Design Drawings","","This paper presents methods for building a comprehensive evaluation resource to assess algorithms that segment and perceptually group 2D mechanical technical drawings. The dataset includes a diverse set of such drawings, with semi-automated annotations for both segments and perceptual groups. Domain experts reviewed these annotations using detailed guidelines to ensure consistency and high-quality labeling. The resource is designed to support researchers improving comprehension and interpretation of 2D mechanical drawings.",{"@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/2d-cross-view-object-segmentation-and-perceptual-grouping-in-computer-aided-design-drawings/649784/",{"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/2d-cross-view-object-segmentation-and-perceptual-grouping-in-computer-aided-design-drawings/649784.png","ImageObject",300,407,{"name":92,"@type":93},"McQueen","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-25","2026-10-24",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What does the paper aim to evaluate for 2D mechanical technical drawings?","Question",{"text":112,"@type":113},"It targets algorithms that perform 2D object segmentation and perceptual grouping within mechanical technical drawing content.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is included in the proposed dataset?",{"text":117,"@type":113},"The dataset contains diverse 2D mechanical technical drawings plus semi-automated annotations for segments and perceptual groups.",{"name":119,"@type":110,"acceptedAnswer":120},"How are the annotations ensured to be reliable?",{"text":121,"@type":113},"Domain experts reviewed the semi-automated annotations following detailed guidelines to maintain consistency and high labeling quality.","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},649784,1792920765,{"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":8,"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":143,"read_time":144},5909890329169,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","This ICCV workshop paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.  \n2D Cross-View Object Segmentation and Perceptual Grouping in Computer-Aided Design Drawings  \nMohamed Dhia Elhak BESBES Capgemini  \n[mohamed-dhia-elhak.besbes@capgemini.com](mohamed-dhia-elhak.besbes@capgemini.com)  \nZahra VAHIDI FERDOUSI Capgemini  \n[zahra.vahidi-ferdousi@capgemini.com](zahra.vahidi-ferdousi@capgemini.com)  \nHedi TABIAUniv Paris Saclay  \n[hedi.tabia@univevry.com](hedi.tabia@univevry.com)  \nMouna FRADI Capgemini  \n[mouna.fradi@capgemini.com](mouna.fradi@capgemini.com)  \nAbstract  \nThis paper introduces our methods in creating a comprehensive evaluation resource for assessing the capabilities of algorithms aimed at segmenting and perceptually grouping 2D mechanical technical drawings. Our dataset encompasses a diverse collection of such drawings, accompanied by semi-automated annotations of segments and groups. These annotations were reviewed by domain experts, following detailed guidelines to ensure both consistency and top-notch quality. The dataset is intended to serve as an invaluable asset for researchers dedicated to advancing techniques that enhance the comprehension and interpretation of 2D mechanical drawings.  \n1. Introduction  \nTechnical drawings serve as a universal language that enables engineers, designers, and manufacturers to effectively communicate intricate details and specifications of a product. By capturing essential dimensions, tolerances, and geometric configurations, technical drawings lay the foundation for successful and precise manufacturing processes.  \nOne of the primary purposes of technical drawings is to convey critical tolerance information that ensures the accuracy and functionality of the end product. Tolerances define the permissible variations in dimensions, ensuring that the manufactured components fit together seamlessly and perform as intended. These drawings provide a visual representation of how different parts fit and interact within an assembly, aiding in the identification of potential issues and streamlining the production process. However, understanding and interpreting these drawings can be challenging due to the complexity and variability of their content. To address this problem, researchers have developed vari-  \nous techniques for automatically segmenting and grouping the elements in technical drawings, with the goal of improving their readability and comprehension. There has been asignificant amount of research on techniques for segmenting and perceptually grouping elements in 2D mechanical technical drawings.  \nDatasets In research papers, most of the work done on technical drawings refers to the architecture, engineering and construction industries. We can cite [6], which presentsa large-scale real-world CAD drawing dataset of floor plans. Similarly to vehicle conception drawings, architecture drawings are composed of line segments, arcs, curves, and texts.  \nThe authors of [1] proposed a benchmark of four kinds of drawings: mechanical, architectural, and two distinct types of utility drawings.  \nOn the other hand, segmentation datasets encompass a wide range of domains, offering extensive coverage. The authors of [22] propose a large dataset for semantic segmentation of medical images. The analysis of urban scenes is another application([20], [2]), used essentially for autonomous driving or urban security concerns. The authors of [12] propose a composite dataset from different domains (Cityscapes [2], Mapillary [16], COCO [13], ADE20K [27], and others), in order to do cross-domain semantic segmentation by training a single generic model that can be applied to images even not seen during training.  \n(Video object segmentation [18], instance segmentation [8].)  \nMulti-view segmentation in also applied to different fieldsand imag","cbCaiaUax31avfHO","https://ap.wps.com/l/cbCaiaUax31avfHO","pdf",1395814,"English","# Abstract\n# 1. Introduction\n## Technical drawings analysis","[{\"question\":\"What does the paper aim to evaluate for 2D mechanical technical drawings?\",\"answer\":\"It targets algorithms that perform 2D object segmentation and perceptual grouping within mechanical technical drawing content.\"},{\"question\":\"What is included in the proposed dataset?\",\"answer\":\"The dataset contains diverse 2D mechanical technical drawings plus semi-automated annotations for segments and perceptual groups.\"},{\"question\":\"How are the annotations ensured to be reliable?\",\"answer\":\"Domain experts reviewed the semi-automated annotations following detailed guidelines to maintain consistency and high labeling quality.\"}]","2D Cross-View Object Segmentation and Perceptual Grouping in Computer-Aided Design Drawings | PDF",1792807025,25]