[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-134795-en":3,"doc-seo-134795-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},134795,549768072016,"WPS_1786070896","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",6,"Technology","No Pixel Left Behind - Filling Gaps in Anime Colorization","Animation production workflows often rely on digital colorization of line art, yet tiny unpainted enclosed regions (“gaps”) are frequently overlooked and require time-consuming manual detection and filling. A formative study of Japanese anime pipelines identified this usability and workload bottleneck despite common use of paint-bucket tools. GapFill is a production-oriented system using domain-specific deep learning to suggest context-appropriate fill colors, improving performance and usability with professional colorists.","No Pixel Left Behind: Filling Gaps in Anime Colorization  \nMasahiro Kono The University of Tokyo  \nTokyo, Japan [marckono2825@g.ecc.u-tokyo.ac.jp](marckono2825@g.ecc.u-tokyo.ac.jp)  \nAkinobu Maejima  \nR&DOLM Digital, Inc. Tokyo, Japan Advanced Research Group IMAGICA GROUP, Inc. Tokyo, Japan  \n[akinobu.maejima@olm.co.jp](akinobu.maejima@olm.co.jp)  \nYuki Koyama The University of Tokyo  \nTokyo, Japan [koyama@pe.t.u-tokyo.ac.jp](koyama@pe.t.u-tokyo.ac.jp)  \nYotam Sechayk The University of Tokyo  \nTokyo, Japan [sechayk-yotam@g.ecc.u-tokyo.ac.jp](sechayk-yotam@g.ecc.u-tokyo.ac.jp)  \nTakeo Igarashi  \nThe University of Tokyo Tokyo, Japan [takeo@acm.org](takeo@acm.org)  \nFigure 1: GapFill assists professional anime colorists in addressing small unpainted gaps. (a) Colorization with the paint bucket often (b) leaves small enclosed regions (“gaps”) unpainted. When GapFill is activated,(c) gap detection with circular highlights is triggered, and (d) these gaps are temporarily filled with suggested colors using our domain-specific deep learning method.(e) Hovering over a highlight shows a magnified view, allowing inspection without zooming. (f) Dragging within a highlight activates a color-pick mode for correcting the suggestion. (g) Users can sweep across correct suggestions to apply them at once.  \nAbstract  \nAnimation production workflows often involve digital colorization of line art, where small unpainted regions (“gaps”) frequently occur and remain an underexplored challenge. We conducted a formative study in Japanese animation (anime) pipelines and found that while the paint bucket tool is widely used for base coloring, tiny enclosed areas are frequently overlooked, resulting in time-consuming manual detection and filling. We introduce GapFill, a tool grounded in professional practices that reduces the effort of gap detection, zooming, and color selection. Our deep-learning method suggests  \nThis work is licensed under a Creative Commons Attribution-NonCommercialNoDerivatives 4.0 International License.  \nCHI’26, Barcelona, Spain  \n© 2026 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-2278-3/26/04  \n[https://doi.org/10.1145/3772318.3790968](https://doi.org/10.1145/3772318.3790968)  \nappropriate fill colors by referencing surrounding regions, leveraging the flat-color nature of anime-style images. In a user study with 13 professional colorists, our system improved performance and usability in gap-filling tasks over conventional methods. The study also suggested that prediction accuracy alone is not the primary factor for usability, that appropriate colors can be contextually ambiguous, and that GapFill can complement existing tools depending on users’ trust in new AI-powered assistance.  \nCCS Concepts  \n• Human-centered computing → Graphical user interfaces; • Applied computing → Media arts; • Computing methodologies → Image processing.  \nKeywords  \nCreativity Support Tools, Anime, Colorization, Digital Painting, Deep Learning, Professional Workflow, Human–AI Collaboration  \nACM Reference Format:  \nMasahiro Kono, Akinobu Maejima, Yuki Koyama, Yotam Sechayk, and Takeo Igarashi. 2026. No Pixel Left Behind: Filling Gaps in Anime Colorization. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI’26), April 13–17, 2026, Barcelona, Spain. ACM, New York, NY, USA, 19 pages. [https://doi.org/10.1145/3772318.3790968](https://doi.org/10.1145/3772318.3790968)  \n1 Introduction  \nJapanese animation (anime), deeply rooted in Japanese pop culture, has emerged as a globally recognized form of media art. The anime industry is notable for its cultural influence and economic significance, supported by a rapidly expanding international market [48] and a vast global fan base [47] . Despite a high volume of broadcasts (over 200 titles per year [3]), the colorization process, referring to filling flat colors into each region of hand-drawn line art for every frame, remains largely manual. This reflects the legac","cbCaiacxjYZ8TVU9","https://ap.wps.com/l/cbCaiacxjYZ8TVU9","pdf",3509318,8,1,19,"English","en",105,"# Introduction\n## Gap challenge in anime colorization\n## Formative study of professional workflows\n## GapFill tool and deep-learning approach","[{\"question\":\"What problem does GapFill address in anime colorization?\",\"answer\":\"GapFill targets small unpainted enclosed regions (“gaps”) that often remain after using common paint-bucket tools. These gaps are hard to visually detect and cause costly retakes if not filled correctly.\"},{\"question\":\"How does GapFill help users during the coloring workflow?\",\"answer\":\"GapFill detects gaps and suggests appropriate fill colors based on surrounding regions and the flat-color nature of anime images. It supports inspection and correction through interactive highlight-based operations.\"},{\"question\":\"What did the user study with professional colorists show?\",\"answer\":\"With 13 professional colorists, GapFill improved both performance and usability for gap-filling tasks versus conventional methods. The study also indicated that usability depends on more than prediction accuracy alone.\"}]","No Pixel Left Behind - Filling Gaps in Anime Colorization | PDF",1787299641,48,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"no-pixel-left-behind-filling-gaps-in-anime-colorization","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/technology/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/no-pixel-left-behind-filling-gaps-in-anime-colorization/134795/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-31","2026-08-21",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does GapFill address in anime colorization?","Question",{"text":77,"@type":78},"GapFill targets small unpainted enclosed regions (“gaps”) that often remain after using common paint-bucket tools. These gaps are hard to visually detect and cause costly retakes if not filled correctly.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How does GapFill help users during the coloring workflow?",{"text":82,"@type":78},"GapFill detects gaps and suggests appropriate fill colors based on surrounding regions and the flat-color nature of anime images. It supports inspection and correction through interactive highlight-based operations.",{"name":84,"@type":75,"acceptedAnswer":85},"What did the user study with professional colorists show?",{"text":86,"@type":78},"With 13 professional colorists, GapFill improved both performance and usability for gap-filling tasks versus conventional methods. The study also indicated that usability depends on more than prediction accuracy alone.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,115,120,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":113,"slug":114},50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":122,"slug":123},"Research & Report",30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},"General","general"]