[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-134674-en":3,"doc-seo-134674-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},134674,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Generating an ω -Tile Set for Texture Synthesis - Abstract and Keywords","This paper presents an effective approach to generate a set of small textures from an input texture that can be tiled together to synthesize large textures. The method enables realistic, efficient texturing of large areas while using only a small amount of texture memory. It generates fewer tiles that embed more texture patterns with less conspicuous seams than earlier techniques, producing large results that resemble continuous regions of the input and avoid highly repetitive patterns, especially for detailed or relatively large features and distinctive colors.","Generating an ω -Tile Set for Texture Synthesis  \nTuen-Young Ng†, Conghua Wen, Tiow-Seng Tan† Xinyu Zhang‡, Young J. Kim‡  \nSchool of Computing  \nNational University of Singapore, Singapore  \nDept of Computer Science and Engineering  \nEwha Womans University, Korea  \nFigure 1: Four small patches are extracted from an input texture to form 16 different texturing blocks; an example of such a block is shown on the left. A tile is cut from the center of each block to obtain in total 16 ω-tiles as shown on the right. The color at each corner of an ω-tile indicates the color of the patch that contributes to the corner. The interior (shown within each curve) of each ω-tile is obtained by sampling another patch from the input texture.  \nAbstract  \nThis paper presents an effective approach to generate a set of small textures from an input texture that can be tiled together to synthesize large textures. Such a small set can be useful in texturing any large area realistically and efficiently while consuming only a small amount of texture memory. Our approach is advantageous in its ability to generate a smaller number of tiles that can embed much more texture patterns and with less conspicuous seams within each tile than earlier approaches. As a result, our approach can generate large textures that look as if each were from a continuous part of the input texture while avoiding highly repetitive patterns. In general, our approach performs very well and shows a particular strength, compared to earlier approaches, for input textures of elaborate or relatively large features, or with distinctive colors.  \nCR Categories: I.3.3 [Computer Graphics]: Picture/Image Generation; I.3.6: [Computer Graphics]: Methodology and Techniques; I.4.3 [Image Processing]: Smoothing  \nKeywords: non-repetitive tiling, Wang tile, image generation  \n1. INTRODUCTION  \nFrom a given input texture, texture synthesis is to generate large textures, i.e. synthesized textures that maintain the underlying global distribution pattern of the input texture. In some applications, a large synthesized texture is pre-computed from a small input texture to texture map a large area; see, for example, the pixel- [4, 6, 9, 21] and patch-based [1, 5, 13, 15] synthesis approaches. In other, a set of small textures is pre-computed from an input texture for use to tile into a large texture (during real-time rendering) . This avoids the need for a large texture memory when texturing a large area. The main focus of this paper lies in the latter usage of texture synthesis.  \n†e-mails: {ngtuenyo, [tants}@comp.nus.edu.sg](tants}@comp.nus.edu.sg)[ ](tants}@comp.nus.edu.sg)‡e-mails: {zhangxy, [kimy}@ewha.ac.kr](kimy}@ewha.ac.kr)  \nThe 2005 Computer Graphics International, 22-24 June, Stony Brook, New York, USA.  \nOur work is motivated by the approach provided in [3] that generates a set of square texture tiles, called Wang tiles, for tiling to form large textures. We propose a novel and competitive approach to create a new set of texture tiles, called ω-tiles. The approach first extracts four small patches from an input texture Sto arrange them into blocks to derive ω-tiles; see Figure 1.  \nOur approach addresses the following three important issues arising in generating a set of tiles for texture synthesis:  \n• The content of each tile should look as if it were a continuous part ofS.  \n• Tiles should be seamless across the boundaries in their synthesized textures.  \n• A large synthesized texture from these tiles should maintain the underlying global distribution pattern ofS.  \nOur approach, first of all, addresses the possible seams occurring inside a tile by providing a large search space so as to control the seams that can result from combining patches in S. Furthermore, seams within each tile form a closed curve (rather than a cross as in previous approaches), and they can be softened using a Poisson approach [16] .  \nSecondly, the seams between two ω-tiles adjacent to eachother are avoided by","cbCaicKYldP5GTVc","https://ap.wps.com/l/cbCaicKYldP5GTVc","pdf",2967552,1,"English","en",105,"# INTRODUCTION\n## Motivation and usage of tile sets for texture synthesis\n## Overview of the proposed ω-tiles\n# PREVIOUS WORK\n## Procedural texturing and its limits\n## Pattern-based texturing and related methods","[{\"question\":\"What does the proposed ω-tile set achieve in texture synthesis?\",\"answer\":\"It generates a small set of tiles from an input texture that can be tiled to synthesize large textures realistically and efficiently.\"},{\"question\":\"Why does the method reduce visible seams and repetitiveness?\",\"answer\":\"It uses a larger search space to control seam placement within tiles, softens seams using a Poisson approach, and avoids seams between adjacent tiles by matching patch sides while handling junctions carefully.\"},{\"question\":\"What kinds of input textures does the approach perform particularly well on?\",\"answer\":\"It performs very well for input textures with elaborate or relatively large features and for textures with distinctive colors.\"}]","Generating an ω -Tile Set for Texture Synthesis - Abstract and Keywords | PDF",1787285802,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"generating-an-tile-set-for-texture-synthesis-abstract-and-keywords","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/generating-an-tile-set-for-texture-synthesis-abstract-and-keywords/134674/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-24","2026-08-21",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 does the proposed ω-tile set achieve in texture synthesis?","Question",{"text":75,"@type":76},"It generates a small set of tiles from an input texture that can be tiled to synthesize large textures realistically and efficiently.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why does the method reduce visible seams and repetitiveness?",{"text":80,"@type":76},"It uses a larger search space to control seam placement within tiles, softens seams using a Poisson approach, and avoids seams between adjacent tiles by matching patch sides while handling junctions carefully.",{"name":82,"@type":73,"acceptedAnswer":83},"What kinds of input textures does the approach perform particularly well on?",{"text":84,"@type":76},"It performs very well for input textures with elaborate or relatively large features and for textures with distinctive colors.","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":23},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":28,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":28,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]