[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83350-en":3,"doc-seo-83350-105":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},83350,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Leveraging Color Naming for Image Enhancement","Image enhancement through user-friendly, controllable edits remains challenging in computer vision. Existing deep-learning approaches learn from paired raw–retouched datasets but often lack interpretability and do not provide a suitable parameterization for user adjustments. NamedCurves+ leverages universal color naming by integrating color names into a learning framework, using named Bezier tone curves for global control and a transformer block for context-aware local edits. Extensive experiments show superior results on retouching, tone mapping, and exposure correction, with explainable, interactive user customization.","Leveraging Color Naming for Image Enhancement  \nDavid Serrano-Lozano, Luis Herranz, Michael S. Brown, Javier Vazquez-Corral  \narXiv :2607 .08 185v 1 [ cs .CV] 9 Jul 2026  \nAbstract—Enhancing images to make them visually appealing is a persistent challenge in computer vision. Many deep-learning methods train models on paired datasets to replicate expert editing styles. However, these approaches struggle with two key issues: (1) interpretability and (2) a parametrization suitable for user adjustments. To address these challenges, we present NamedCurves+, an approach inspired by the concept of Color Naming, a universal set of familiar colors widely used in software tools for intuitive editing. Our method integrates color names into a learning-based framework, enabling global adjustments for each named color through tone curves. To address local image variations, we incorporate a transformer block that captures spatial dependencies, enabling context-aware edits across the image. NamedCurves+ enhances the retouching process’s interpretability and supports user interaction, allowing flexible modifications of individual tone curves to refine the retouched image according to personal preferences. Extensive experiments on tasks such as image retouching, tone mapping, and exposure correction demonstrate that NamedCurves+ outperforms stateof-the-art methods. Notably, our approach is both explainable, as the tone curves explicitly represent how each color name contributes to the enhancement, and interactive, allowing users to customize the retouching process and achieve results tailored to their liking. Source code and models will be publicly available at: [https://namedcurves.github.io](https://namedcurves.github.io).  \nIndex Terms—Image Enhancement, Image Retouching, Color Editing, Color Naming  \nI. INTRODUCTION  \nCOLOR plays a vital role in photography, enhancing focal  \npoints, evoking emotions, and enriching storytelling. Whether through vibrant hues or subtle tones, understanding the importance of colors is crucial for photographers seeking to elicit specific responses. Despite significant advancementsin camera technology, both amateur and professional photographers often resort to post-capture image enhancement to improve image quality. However, manual image editing poses challenges for those lacking expertise, time, or a welldeveloped aesthetic sense.  \nA potential solution to avoid manual adjustment lies in learning-based methods, where deep neural networks (DNN) model the editing style of skilled photographers or colorists. These models typically leverage paired datasets of raw and expert-retouched images. While effective in many scenarios, such approaches have critical limitations. Expert aesthetic sense may not always align with individual preferences or specific use cases, leaving certain users dissatisfied with theretouched results. Furthermore, existing methods often rely on approaches such as weighting multiple 3D Look-Up Tables [1]–[4], or employing end-to-end U-Net-like architectures [5]–[7], which offer limited interpretability and prevent  \nDSL and JVC are with the Universitat Autnoma de Barcelona, Spain and the Computer Vision Center, Barcelona, Spain. LH is with the Universidad Politcnica de Madrid, Spain. MSB is with the York University, Toronto, Canada.  \nuser interaction. As a result, users cannot easily adjust the output to suit their specific needs. Compounding the issue, most image-retouching datasets are captured in controlled environments by skilled professionals, while real-world images are often taken by amateurs under varying lighting conditions. This creates significant variability in the amount of light reaching the camera sensor, further complicating the enhancement process. To bridge the gap between the intensive manual adjustments required by software tools and the limited controllability of current automated methods, we propose an approach that mimics the expert’s style while also allowing users to m","cbCaiu8GccYKsdam","https://ap.wps.com/l/cbCaiu8GccYKsdam","pdf",49191473,1,14,"English","en",105,"# Introduction\n## Motivation and challenges\n## Color naming in photo editing\n## Proposed approach: NamedCurves+","[{\"question\":\"What problems do existing learning-based image enhancement methods have?\",\"answer\":\"They often suffer from limited interpretability and an inadequate parameterization for interactive user control, making it difficult for users to steer results toward personal preferences.\"},{\"question\":\"How does NamedCurves+ use color naming to enable controllable edits?\",\"answer\":\"It decomposes the image into color maps tied to six color names and applies Bezier-parameterized global tone curves per named color, so users can adjust tone curves directly.\"},{\"question\":\"How does NamedCurves+ handle local variations in real images?\",\"answer\":\"It incorporates a transformer block that captures spatial dependencies, enabling context-aware edits across the image beyond purely global adjustments.\"}]",1784186939,35,{"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},"leveraging-color-naming-for-image-enhancement","",{"@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/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/leveraging-color-naming-for-image-enhancement/83350/",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 problems do existing learning-based image enhancement methods have?","Question",{"text":74,"@type":75},"They often suffer from limited interpretability and an inadequate parameterization for interactive user control, making it difficult for users to steer results toward personal preferences.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does NamedCurves+ use color naming to enable controllable edits?",{"text":79,"@type":75},"It decomposes the image into color maps tied to six color names and applies Bezier-parameterized global tone curves per named color, so users can adjust tone curves directly.",{"name":81,"@type":72,"acceptedAnswer":82},"How does NamedCurves+ handle local variations in real images?",{"text":83,"@type":75},"It incorporates a transformer block that captures spatial dependencies, enabling context-aware edits across the image beyond purely global adjustments.","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},[92,96,100,104,109,114,119,122,127,130,134],{"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":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"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":105,"slug":137},19,"General","general"]