[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-517762-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-517762-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","state-of-the-art-on-deep-learning-enhanced-rendering-methods-star","State of the Art on Deep Learning-enhanced Rendering Methods - STAR","","Photorealistic rendering of virtual scenes is a core challenge in computer graphics, especially when efficient global illumination remains difficult for conventional pipelines. GPU progress has improved baseline rasterization and Monte Carlo integration, yet rendering still relies heavily on expert shader and scene authoring. Deep learning and computer vision enable neural rendering pipelines that combine learning-based image analysis and synthesis with traditional rendering to enhance realism and efficiency. This state-of-the-art report surveys recent research on neural-network-based renderers, covering general and scene-specific methods.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/state-of-the-art-on-deep-learning-enhanced-rendering-methods-star/517762/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/state-of-the-art-on-deep-learning-enhanced-rendering-methods-star/517762.png","ImageObject",300,407,{"name":42,"@type":43},"lugxt","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-17","2026-10-07",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does deep learning-enhanced rendering aim to solve?","Question",{"text":63,"@type":64},"It targets efficient photorealistic rendering, particularly challenges in handling global illumination effects within traditional rendering pipelines.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the report define deep learning-enhanced rendering methods?",{"text":68,"@type":64},"It focuses on approaches that integrate deep learning and computer vision into rasterization or Monte Carlo integration pipelines to improve rendering, including renderers represented with neural networks.",{"name":70,"@type":61,"acceptedAnswer":71},"Why is neural rendering sensitive to datasets?",{"text":72,"@type":64},"The report notes that rendering quality in neural rendering depends closely on the quantity, distribution, and quality of the input dataset, making high-quality results with limited data an important concern.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},517762,1791483604,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":99,"preview_page_count":33,"preview_urls":145},3985747862600,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","Machine Intelligence Research [www.mi-research.net](www.mi-research.net)  \n20(6), December 2023, 799-821 DOI: 10.1007/s11633-022-1400-x  \nState ofthe Art on Deep Learning-enhanced Rendering Methods  \nQi Wang1 Zhihua Zhong1 Yuchi Huo 2,1 Hujun Bao 1 Rui Wang1  \n1 State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou 310058, China  \n2 Zhejiang Laboratory, Hangzhou 311121, China  \nAbstract: Photorealistic rendering of the virtual world is an important and classic problem in the field of computer graphics. With the development of GPU hardware and continuous research on computer graphics, representing and rendering virtual scenes has become easier and more efficient. However, there are still unresolved challenges in efficiently rendering global illumination effects. At the sametime, machine learning and computer vision provide real-world image analysis and synthesis methods, which can be exploited by computer graphics rendering pipelines. Deep learning-enhanced rendering combines techniques from deep learning and computer vision into the traditional graphics rendering pipeline to enhance existing rasterization or Monte Carlo integration renderers. This state-of-the-art report summarizes recent studies of deep learning-enhanced rendering in the computer graphics community. Specifically, we focus on works of renderers represented using neural networks, whether the scene is represented by neural networks or traditional scene files.  \nThese works are either for general scenes or specific scenes, which are differentiated by the need to retrain the network for new scenes. Keywords: Neural rendering, computer graphics, scene representation, rendering, post-processing.  \nCitation: Q. Wang, Z. Zhong, Y. Huo, H. Bao, R. Wang. State of the art on deep learning-enhanced rendering methods. Machine  \nIntelligence Research, vol.20, no.6, pp.799–821, 2023. [http://doi.org/10.1007/s11633-022-1400-x](http://doi.org/10.1007/s11633-022-1400-x)  \n1 Introduction  \nFor traditional computer graphics, generating photorealistic rendering results of a scene is an important research direction, and researchers have developed a variety of algorithms to solve this problem in recent decades, including modeling complex materials [1−3], sophisticated sampling methods [4, 5], acceleration of global illumination computation [6, 7], etc. These methods are mainly applied in two fields: the rasterization pipeline for real-time rendering that serves the latest video games and the ray tracing pipeline commonly used in the film industry for offline rendering that deals with global illumination effects. Regardless of the rendering pipeline, much timeconsuming manual work by artists and programmers is essential, i.e. , complex and sophisticated renderers or shaders must be written by experienced programmers, and scene construction, including geometry, material textures, lighting conditions, and animations are the responsibility of artists. These preliminary preparations greatly increase the time and capital cost of photorealistic rendering. However, with the rapid development of com-  \nReview  \nManuscript received on July 11, 2022; accepted on November 29, 2022  \nRecommended by Associate Editor Jing-Yi Yu  \nColored figures are available in the online version at [https://link](https://link). [springer.com/journal/11633](springer.com/journal/11633)  \n© Institute of Automation, Chinese Academy of Sciences and Springer-Verlag GmbH Germany, part of Springer Nature 2023  \nputer vision and deep learning research fields in recent years, the combination of traditional graphics rendering pipelines and deep learning provides a new direction to solve the above problems. A bunch of deep generative models of generating high-resolution styled [8] or high-fidelity 2D images have emerged, e.g. , the seminal generative adversarial neural networks (GANs) [9] and their followups [10, 11], also the variational auto encoder networks (VAEs) [12−14] . Reference [15] even realizes the contro","cbCaibcDqkfa5apP","https://ap.wps.com/l/cbCaibcDqkfa5apP","pdf",5384487,24,"English","# Introduction\n## Traditional rendering pipelines and their costs\n## Neural rendering and deep generative models\n## State-of-the-art report scope and classification","[{\"question\":\"What problem does deep learning-enhanced rendering aim to solve?\",\"answer\":\"It targets efficient photorealistic rendering, particularly challenges in handling global illumination effects within traditional rendering pipelines.\"},{\"question\":\"How does the report define deep learning-enhanced rendering methods?\",\"answer\":\"It focuses on approaches that integrate deep learning and computer vision into rasterization or Monte Carlo integration pipelines to improve rendering, including renderers represented with neural networks.\"},{\"question\":\"Why is neural rendering sensitive to datasets?\",\"answer\":\"The report notes that rendering quality in neural rendering depends closely on the quantity, distribution, and quality of the input dataset, making high-quality results with limited data an important concern.\"}]","State of the Art on Deep Learning-enhanced Rendering Methods - STAR | PDF",1791344782,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/458216ba2d254abb49e2a4122fe03b29.webp",983,1390,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/5eaff8bdc855a8b2fdc48f369c86494d.webp",982,1388,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/1fbaaf73bf01defde6411bcfcd0114b1.webp",981,1387,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/659c062598683a9b14418b6a1b6c02ff.webp",980,1385]