[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-134105-105":59,"doc-detail-134105-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","vectorizing-cartoon-animations-paper-contributions","Vectorizing Cartoon Animations - Paper Contributions","","A system for vectorizing 2D raster cartoon animations produces flicker-free results with smaller file sizes and straightforward editability. The method decomposes each frame into semantically meaningful coloured regions and decorative lines, treating lines as special objects to avoid thin over-segmented fragments. An accurate decomposition algorithm supports an arbitrary color model per region, while a patch-based universal background and foreground extraction ensure temporal coherence.",{"@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/vectorizing-cartoon-animations-paper-contributions/134105/",{"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/vectorizing-cartoon-animations-paper-contributions/134105.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-20","2026-08-20",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How does the system achieve flicker-free vector animation across frames?","Question",{"text":112,"@type":113},"It reconstructs a single patch-based background shared across all frames, then separately extracts foreground regions. This layered representation maintains temporal coherence between frames.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What are the main technical contributions described in the paper?",{"text":117,"@type":113},"The paper introduces a new trapped-ball segmentation method, handles decorative lines separately as special objects during decomposition, and extracts a single patch-based background over all frames to support consistent flicker-free animations.",{"name":119,"@type":110,"acceptedAnswer":120},"What is the role of the trapped-ball segmentation method?",{"text":121,"@type":113},"It segments each frame into regions guided by edges while coping with gaps. The method is fast, supports nonuniformly colored regions, and enables robust segmentation even when region edges are imperfectly linked.","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},134105,1787234018,{"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":34,"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":41},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Vectorizing Cartoon Animations  \nSonghai Zhang 1 Tao Chen 1 Yi-Fei Zhang 1 Shi-Min Hu 1 Ralph R. Martin2  \n1Tsinghua University 2 Cardiff University  \nAbstract—We present a system for vectorizing 2D raster format carton animations. The output animations are visually flicker free, smaller in file size, and easy to edit. We identify decorative lines separately from coloured regions. We use an accurate and semantically meaningful image decomposition algorithm which supports an arbitrary color model for each region. To ensure temporal coherence in the output cartoon, we reconstruct a universal background for all frames, and separately extract foreground regions. Simple user-assistance is required to complete the background. Each region and decorative line is vectorized and stored together with their motions from frame to frame.  \nThe significant novel contributions of this paper are: (i) the new trapped ball segmentation method, which is fast, supports nonuniformly colored regions, and allows robust region segmentation even in the presence of imperfectly linked region edges, (ii) the separate handling of decorative lines as special objects during image decomposition, which avoids results containing multiple short, thin over-segmented regions, and (iii) extraction of a single patch-based background over all frames, which provides a basis for consistent, flicker-free animations.  \nIndex Terms—Cartoon vectorization, Trapped-ball method, Image decomposition, Foreground extraction  \nI. INTRODUCTION  \nCartoon animation, i.e. cel animation, has a long history, resulting in a large body of artistic work. Children and adults enjoy the stylized characters, the drawing and animation styles, plots, and soundtracks. Currently, such cultural heritage is preserved and disseminated as digital video after conversion from film using telecine. Such video is in raster format.  \nHowever, animated 2D cartoons intrinsically have a vectorized nature. Cartoon making has a relatively fixed composition procedure, including an unchanging but moving background, and an animated foreground. In comparison to real-world videos, 2D cartoon animations have simpler, more artificial contents, composed of regularly (but not necessarily uniformly) colored regions, and wide decorative lines, as shown for example in Fig.2 .  \nThis particular nature of 2D cartoons means that there are potential advantages in converting them to vector format:  \n² a vector format will generally allow higher compression ratios for storage and transmission than raster format, because of the small number of regions which can be described by simple colour models,  \n² the vector format is resolution independent, readily allowing display on devices with differing capabilities,  \n² a meaningful vector representation allows the cartoon tobe much more easily edited, [e.g. to](e.g. to) change the location  \nFig. 1. left column: Original videos; right column: Vectorization results showing region boundaries and decorative lines  \nof a character in a scene, or to add new objects in front of some existing objects and behind others,  \n² a meaningful vector representation is much more useful for multimedia information retrieval, allowing a search tobe made for objects of a particular shape,  \n² undesirable artifacts caused by lossy raster compression will be removed: instead regions will be strongly coloured, with strong edges, which better fits the artistic style of cartoons. This in turn allows better quality of video to be transmitted if limited bandwidth is available, and also has potential applications to cartoon restoration.  \nIn recent years, various approaches have been proposed for vectorizing rasterized images [1], [2], and commercial packages exist, e.g. Stanford VectorMagic [3] . However, these do not take into account the particular features of cartoon  \nFig. 2. Cartoon gallery  \nanimations, and in particular tend to suffer from oversegmentation. Furthermore, none of them provides temporal coherence. ","cbCaihCzqyjbSiMG","https://ap.wps.com/l/cbCaihCzqyjbSiMG","pdf",19101222,12,"English","# Introduction\n## Motivation for Vectorizing Cartoons\n## Advantages of Vector Format\n## Challenges in 2D Cartoon Vectorization\n## Key Method Overview","[{\"question\":\"How does the system achieve flicker-free vector animation across frames?\",\"answer\":\"It reconstructs a single patch-based background shared across all frames, then separately extracts foreground regions. This layered representation maintains temporal coherence between frames.\"},{\"question\":\"What are the main technical contributions described in the paper?\",\"answer\":\"The paper introduces a new trapped-ball segmentation method, handles decorative lines separately as special objects during decomposition, and extracts a single patch-based background over all frames to support consistent flicker-free animations.\"},{\"question\":\"What is the role of the trapped-ball segmentation method?\",\"answer\":\"It segments each frame into regions guided by edges while coping with gaps. The method is fast, supports nonuniformly colored regions, and enables robust segmentation even when region edges are imperfectly linked.\"}]","Vectorizing Cartoon Animations - Paper Contributions | PDF"]