[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-662740-105":59,"doc-detail-662740-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","drawing2cad-sequence-to-sequence-learning-for-cad-generation-from-vector-drawings","Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings","","Computer-Aided Design (CAD) generative modeling is transforming industrial applications, yet the step of automatically producing parametric CAD from 2D engineering drawings remains insufficiently explored. Drawing2CAD addresses this gap by casting CAD generation as sequence-to-sequence learning: vector drawing primitives guide the production of parametric CAD operations while preserving geometric precision and design intent. The method is trained and evaluated using CAD-VGDrawing and reported experiments validate its effectiveness.",{"@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/drawing2cad-sequence-to-sequence-learning-for-cad-generation-from-vector-drawings/662740/",{"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/drawing2cad-sequence-to-sequence-learning-for-cad-generation-from-vector-drawings/662740.png","ImageObject",300,407,{"name":92,"@type":93},"Blue Pony","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-28",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},"What problem does Drawing2CAD target?","Question",{"text":112,"@type":113},"It targets the automatic generation of parametric CAD models from 2D vector engineering drawings in SVG format, which is described as underexplored compared with other input modalities.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is CAD generation formulated in Drawing2CAD?",{"text":117,"@type":113},"CAD generation is reframed as a sequence-to-sequence learning problem where vector drawing primitives directly inform the generation of parametric CAD operations.",{"name":119,"@type":110,"acceptedAnswer":120},"What are the key technical components and how are they evaluated?",{"text":121,"@type":113},"Drawing2CAD uses a network-friendly vector primitive representation, a dual-decoder transformer architecture to decouple command type and parameter generation, and a soft target distribution loss. It is trained and tested on the CAD-VGDrawing dataset with thorough experiments to demonstrate effectiveness.","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},662740,1793222207,{"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":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":144},962090760266,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings  \narXiv :2508 . 18733v5 [ cs .CV] 11 Sep 2025  \nFeiwei Qin∗ Hangzhou Dianzi University Hangzhou, China [qinfeiwei@hdu.edu.cn](qinfeiwei@hdu.edu.cn)  \nChangmiao Wang  \nShenzhen Research Institute of Big Data Shenzhen, China [cmwangalbert@gmail.com](cmwangalbert@gmail.com)  \nShichao Lu∗ Hangzhou Dianzi University Hangzhou, China [lushichao@hdu.edu.cn](lushichao@hdu.edu.cn)  \nMeie Fang† Guangzhou University Guangzhou, China [fme@gzhu.edu.cn](fme@gzhu.edu.cn)  \nJunhao Hou∗ Zhejiang University Hangzhou, China [junhaohou@zju.edu.cn](junhaohou@zju.edu.cn)  \nLigang Liu† University of Science and Technology of China Hefei, China [lgliu@ustc.edu.cn](lgliu@ustc.edu.cn)  \nSVG drawing process: Parametrized command sequence:  \nParametrized command sequence:  \nSOL 1 : ∅  \nL2 : (0, 3)  \nL3 : (2, 0)  \nL4 : (3, 2)  \nA5 : (0, 3, π, 0)  \nSOL 6 : ∅  \nE7 : (0, 0, 0, 0, 0, 0, 1, 1, 0, New body, One-sided)  \nSOL 8 : ∅  \n R9 : (3, 1, 0.5)  \nSOL 10 : ∅  \nE11 : (0, 0, 0, 0, 0, 0, 1, 2, 0, Cut, One-sided)  \nEOS 12 : ∅  \nFigure 1: An intuitive comparison of SVG drawing and CAD construction processes. Both SVG drawing and CAD construction rely on a specific set of commands, and their respective processes can be formally represented as parametric command sequences with a unified structural format.  \nAbstract  \nComputer-Aided Design (CAD) generative modeling is driving significant innovations across industrial applications. Recent works have shown remarkable progress in creating solid models from various inputs such as point clouds, meshes, and text descriptions. However, these methods fundamentally diverge from traditional industrial workflows that begin with 2D engineering drawings. The automatic generation of parametric CAD models from these 2D vector drawings remains underexplored despite being a critical step in engineering design. To address this gap, our key insight is to reframe CAD generation as a sequence-to-sequence learning problem where vector drawing primitives directly inform the generation of parametric CAD operations, preserving geometric precision and design intent throughout the transformation process.  \n∗ Equal contributions.†Corresponding authors.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nMM’25, Dublin, Ireland  \n© 2025 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 979-8-4007-2035-2/2025/10  \n[https://doi.org/10.1145/3746027.3755782](https://doi.org/10.1145/3746027.3755782)  \nWe propose Drawing2CAD, a framework with three key technical components: a network-friendly vector primitive representation that preserves precise geometric information, a dual-decoder transformer architecture that decouples command type and parameter generation while maintaining precise correspondence, and a soft target distribution loss function accommodating inherent flexibility in CAD parameters. To train and evaluate Drawing2CAD, we create CAD-VGDrawing, a dataset of paired engineering drawings and parametric CAD models, and conduct thorough experiments to demonstrate the effectiveness of our method. Code and dataset are available at [https://github.com/lllssc/Drawing2CAD](https://github.com/lllssc/Drawing2CAD).  \nCCS Concepts  \n• Computing methodologies → Computer vision tasks.  \nKeywords  \nCAD generative modeling; Engineering drawings; Vecto","cbCaipowPZPYOF3p","https://ap.wps.com/l/cbCaipowPZPYOF3p","pdf",3005997,11,"English","# Abstract\n# CCS Concepts\n# Keywords\n# 1 Introduction","[{\"question\":\"What problem does Drawing2CAD target?\",\"answer\":\"It targets the automatic generation of parametric CAD models from 2D vector engineering drawings in SVG format, which is described as underexplored compared with other input modalities.\"},{\"question\":\"How is CAD generation formulated in Drawing2CAD?\",\"answer\":\"CAD generation is reframed as a sequence-to-sequence learning problem where vector drawing primitives directly inform the generation of parametric CAD operations.\"},{\"question\":\"What are the key technical components and how are they evaluated?\",\"answer\":\"Drawing2CAD uses a network-friendly vector primitive representation, a dual-decoder transformer architecture to decouple command type and parameter generation, and a soft target distribution loss. It is trained and tested on the CAD-VGDrawing dataset with thorough experiments to demonstrate effectiveness.\"}]","Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings | PDF",28]