[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84083-en":3,"doc-seo-84083-105":30,"detail-sidebar-cat-0-en-105":91},{"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":13,"seo_description":14,"update_tm":28,"read_time":29},84083,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control","Image outpainting expands an image beyond its original borders while preserving seamless style integration and globally coherent scene completion. Despite recent progress from diffusion-based methods, high-resolution artwork outpainting still faces three limitations: missing reliable global planning, weak spatial controllability beyond text prompts, and high inference latency from sequential patch generation. A global blueprint-guided two-stage diffusion framework is proposed to enable layout-controlled, efficient parallel synthesis. Stage 1 predicts a low-resolution structural blueprint, while Stage 2 generates high-resolution local patches in parallel for faster, more consistent results.","arXiv :2607 .06 162v 1 [ cs .CV] 7 Jul 2026  \nHigh-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control  \nJunha Kim, Hyunjoon Park, and Donghyeon Cho†  \nHanyang University, Seoul, Republic of Korea {poohoh,junippini83,[doncho}@hanyang.ac.kr](doncho}@hanyang.ac.kr)  \nAbstract. Image outpainting extends an image beyond its original borders, requiring seamless style integration and globally coherent scene completion. Building on the success of diffusion models, recent methods have achieved substantial improvements in visual quality. In practice, however, high-resolution outpainting is commonly performed via progressive expansion around a fixed source image, particularly in artwork scenarios. Despite this progress, existing approaches still suffer from three key limitations: (i) the absence of a reliable global planning mechanism, which leads to structural instability and error accumulation at high resolutions; (ii) limited spatial controllability beyond text prompts, making it difficult to place objects at user-specified locations; and (iii) high inference latency caused by inherently sequential patch generation. To address these issues, we propose a global blueprint-guided two-stage diffusion framework for layout-controllable high-resolution outpainting with efficient parallel synthesis. In Stage 1, we generate a low-resolution global blueprint using a layout adapter that injects bounding-box conditions into a Stable Diffusion inpainting backbone, producing a globally consistent structural plan while extracting global guidance features. In Stage 2, we synthesize high-resolution local patches in parallel by injecting the blueprint-derived global guidance and initializing each patch from the blueprint using the low-frequency preservation property of forward diffusion. This design eliminates sequential dependency while maintaining global coherence. Extensive experiments on large-scale artwork datasets demonstrate improved visual fidelity, stronger semantic consistency, and substantially reduced inference time compared to prior baselines, while uniquely supporting explicit layout control for artwork outpainting. Our code will be available at [https://github.com/poohoh/BlueOut](https://github.com/poohoh/BlueOut).  \nKeywords: Outpainting · Artworks · High-resolution · Layout control  \n1 Introduction  \nImage outpainting extends an image beyond its original borders. The key chal  \nlenge lies in seamless integration, which requires matching the style, color, and context of the source image rather than merely enlarging the canvas. Although † Corresponding author.  \n2 J. Kim et al.  \nFig. 1: Challenges in High-resolution Artwork Outpainting. (a) Progressive methods accumulate errors without global planning; our blueprint-guided approach maintains global coherence. (b) Text-only conditioning struggles with object placement; our layout-conditioned framework enables spatial control. (c) Sequential generation incurs high latency; our parallel synthesis achieves up to 2.4× speedup.  \noutpainting is often considered analogous to inpainting, it is inherently more challenging. In inpainting, the target region is surrounded by known pixels, which facilitates reliable context inference. In contrast, outpainting synthesizes content in unbounded regions outside the image, introducing substantially greater uncertainty. Consequently, successful outpainting requires not only plausible local synthesis but also an accurate understanding of the global context to maintain structural naturalness and contextual consistency. Moreover, in artwork outpainting for immersive display applications such as large-scale projection and VR/AR environments [10], legacy paintings must be adapted to new canvas sizes while preserving their original visual fidelity and aspect ratios. This requirement makes the process highly sensitive to stylistic distortion and compositional imbalance, thereby making accurate global context modeling particularly cr","cbCaimpJPcQ8XKiJ","https://ap.wps.com/l/cbCaimpJPcQ8XKiJ","pdf",46298276,2,1,45,"English","en",105,"# Introduction\n## Challenges in high-resolution artwork outpainting\n## Global blueprint-guided two-stage framework","[{\"question\":\"What problem does high-resolution artwork outpainting address?\",\"answer\":\"It extends an image beyond its borders while keeping the result visually seamless and globally consistent with the original style and context.\"},{\"question\":\"What limitations remain in existing high-resolution outpainting methods?\",\"answer\":\"They lack reliable global planning, provide limited spatial controllability beyond text prompts, and suffer from high latency due to inherently sequential patch generation.\"},{\"question\":\"How does the proposed two-stage blueprint-guided framework improve outpainting quality and speed?\",\"answer\":\"Stage 1 produces a low-resolution global blueprint that ensures structural coherence, and Stage 2 synthesizes high-resolution local patches in parallel using blueprint-derived guidance, removing sequential dependency while maintaining global consistency.\"}]",1784192597,113,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"high-resolution-artwork-outpainting-with-global-blueprint-guidance-and-layout-control","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/high-resolution-artwork-outpainting-with-global-blueprint-guidance-and-layout-control/84083/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does high-resolution artwork outpainting address?","Question",{"text":75,"@type":76},"It extends an image beyond its borders while keeping the result visually seamless and globally consistent with the original style and context.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitations remain in existing high-resolution outpainting methods?",{"text":80,"@type":76},"They lack reliable global planning, provide limited spatial controllability beyond text prompts, and suffer from high latency due to inherently sequential patch generation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed two-stage blueprint-guided framework improve outpainting quality and speed?",{"text":84,"@type":76},"Stage 1 produces a low-resolution global blueprint that ensures structural coherence, and Stage 2 synthesizes high-resolution local patches in parallel using blueprint-derived guidance, removing sequential dependency while maintaining global consistency.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]