[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83437-en":3,"doc-seo-83437-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83437,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",6,"Technology","NamedCurves: Learned Image Enhancement via Color Naming","NamedCurves presents a learning-based image enhancement approach inspired by color-name editing in common photo tools. It decomposes an image into a small set of named colors, then learns global tone-curve adjustments for each color using smooth differential Bezier curves. Modified color-specific components are fused with an attention-based mechanism to mimic spatial, local editing. Experiments on Adobe 5K and PPR10K datasets demonstrate improved results over competing methods using PSNR and color distance (ΔE00).","13 Jul 2024  \nNamedCurves: Learned Image Enhancement via  \nColor Naming  \nDavid Serrano-Lozano 1 ,2 , Luis Herranz3 , Michael S. Brown4 , and Javier Vazquez-Corral 1 ,2  \n1 Computer Vision Center, Barcelona, Spain  \n2 Universitat Autònoma de Barcelona, Barcelona, Spain  \n3 Universidad Autónoma de Madrid, Madrid, Spain  \n4 York University, Toronto, Canada  \n{dserrano,[jvazquez}@cvc.uab.cat](jvazquez}@cvc.uab.cat) , [luis.herranz@uam.es](luis.herranz@uam.es), [mbrown@eecs.yorku.ca](mbrown@eecs.yorku.ca)  \n[namedcurves.github.io](namedcurves.github.io)  \nFig. 1: Column 1 displays an input image corrected by a photo-editing expert (denoted as ground truth) . Our proposed method decomposes the image based on color naming and learns a tone-curve correction to mimic the expert’s style (shown in columns 2-3) . Results comparing the input, our results, and the approach by [21] are reported in terms of the color distance metric ∆E00 .  \nAbstract. A popular method for enhancing images involves learning the style of a professional photo editor using pairs of training images comprised of the original input with the editor-enhanced version. When manipulating images, many editing tools offer a feature that allows the user to manipulate a limited selection of familiar colors. Editing by color name allows easy adjustment of elements like the \"blue\" of the sky orthe \"green\" of trees. Inspired by this approach to color manipulation, we propose NamedCurves, a learning-based image enhancement technique that separates the image into a small set of named colors. Our method learns to globally adjust the image for each specific named color via tone curves and then combines the images using an attention-based fusion mechanism to mimic spatial editing. We demonstrate the effectiveness of our method against several competing methods on the well-known Adobe 5K dataset and the PPR10K dataset, showing notable improvements.  \nKeywords: Color enhancement · Image enhancement · Color naming  \narXiv :2407 .098 92v1 [ cs .CV]  \n2 D. Serrano-Lozano et al.  \n1 Introduction  \nColor plays a vital role in photography, enhancing focal points, evoking emotions, and enriching storytelling. Whether through vibrant hues or subtle tones, understanding the importance of colors is crucial for photographers seeking to evoke specific responses. Despite significant advancements in camera technology, amateurs and professionals still often resort to post-capture image enhancement to enhance an image’s quality. However, manual enhancement can be challenging for those lacking expertise, time, or a well-developed aesthetic sense.  \nA potential solution to avoid manual adjustment is to learn a deep network model that can mimic the image editing style of a skilled photographer or colorist. These methods leverage a dataset of image pairs with the original and corresponding artist-edited images. It is interesting to consider the tools provided to the artists for performing the image editing. Many photo editing software applications (e.g., Adobe Photoshop [1]) provide users with the ability to manipulate the image based on a small set of fixed colors (e.g. , red, green, yellow, orange, blue, purple) . Interestingly, the predefined colors selected by software tools are similar to those linguists have found to be universal across languages [6], a research topic often referred to as color naming.  \nContribution: We propose to leverage the use of color naming decomposition for image enhancement. In particular, we introduce NamedCurves, a learningbased image enhancement method that decomposes images into color names and estimates a tone curve in the form of smooth, differential Bezier curves (see Figure 1) . This is followed by an attention-based fusion scheme that combines the images modified by the individual color curves, simulating local image editing. We compare our method with several state-of-the-art image enhancement methods on the MIT-Adobe-5K and PPR10K datasets. Our color naming sch","cbCait8hgTOZv7Zx","https://ap.wps.com/l/cbCait8hgTOZv7Zx","pdf",5128654,1,24,"English","en",105,"# Introduction\n# Related Work\n## Color Naming","[{\"question\":\"What problem does NamedCurves address in image enhancement?\",\"answer\":\"NamedCurves targets the difficulty of manual post-capture editing by learning an editor-like enhancement process from training image pairs and making adjustments guided by color names.\"},{\"question\":\"How does NamedCurves use color naming in its pipeline?\",\"answer\":\"It decomposes an image into a small set of named colors and learns a tone-curve correction for each named color to control how each color is transformed.\"},{\"question\":\"How are the color-adjusted results combined to mimic local editing?\",\"answer\":\"NamedCurves applies attention-based fusion to combine the individually tone-curved color components, producing effects similar to spatial local edits.\"}]",1784187700,60,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"namedcurves-learned-image-enhancement-via-color-naming","",{"@graph":35,"@context":84},[36,53,67],{"@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/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/namedcurves-learned-image-enhancement-via-color-naming/83437/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does NamedCurves address in image enhancement?","Question",{"text":74,"@type":75},"NamedCurves targets the difficulty of manual post-capture editing by learning an editor-like enhancement process from training image pairs and making adjustments guided by color names.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does NamedCurves use color naming in its pipeline?",{"text":79,"@type":75},"It decomposes an image into a small set of named colors and learns a tone-curve correction for each named color to control how each color is transformed.",{"name":81,"@type":72,"acceptedAnswer":82},"How are the color-adjusted results combined to mimic local editing?",{"text":83,"@type":75},"NamedCurves applies attention-based fusion to combine the individually tone-curved color components, producing effects similar to spatial local edits.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,111,116,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":28,"slug":107},5,"Comic","comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":109,"slug":110},50,"technology",{"id":112,"doc_module":4,"doc_module_name":45,"category_name":113,"show_sort_weight":114,"slug":115},7,"Healthcare",40,"healthcare",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":118,"show_sort_weight":119,"slug":120},8,"Research & Report",30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]