[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81624-en":3,"doc-seo-81624-105":30,"detail-sidebar-cat-0-en-105":84},{"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},81624,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing","Neural Radiance Fields (NeRFs) achieve photorealistic novel-view rendering, yet dynamic illumination changes remain unsolved. RehearsalNeRF addresses illumination-radiance ambiguity by learning disentangled neural fields under severe lighting variation. It uses rehearsal-stage video captured under stable lighting as a prior, enforcing geometric consistency across lighting conditions. A learnable temporal lighting vector disentangles projected light colors from scene radiance, and dynamic objects are reconstructed via interactive masks, with optical-flow regularization for color decoupling. Results show robust novel-view synthesis and scene editing under dynamic illumination.","arXiv :2603 .27948v3 [ cs .CV] 10 Jul 2026  \nRehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing  \nChangyeon Won 1†, Hyunjun Jung 1†, Jungu Cho 1,3 ,  \nSeonmi Park 1 , Chi-Hoon Lee3 , Hae-Gon Jeon2*  \n1 Department of AI Convergence, GIST, Gwangju, Korea.  \n2 Department of Artificial Intelligence, Yonsei University, Seoul, Korea.  \n3 AI R&D Division, CJ Corporation, Seoul, Korea.  \n*Corresponding author(s). E-mail(s): [earboll@yonsei.ac.kr](earboll@yonsei.ac.kr) ; Contributing authors: [cywon1997@gm.gist.ac.kr](cywon1997@gm.gist.ac.kr) ;  \n[hyunjun.jung@gm.gist.ac.kr](hyunjun.jung@gm.gist.ac.kr) ; [jungu.cho@cj.net](jungu.cho@cj.net) ; [bluesky1000@gm.gist.ac.kr](bluesky1000@gm.gist.ac.kr) ; [chi.lee@cj.net](chi.lee@cj.net) ;  \n†These authors contributed equally to this work.  \nAbstract  \nAlthough there has been significant progress in neural radiance fields, an issue on dynamic illumination changes still remains unsolved. Different from relevant works that parameterize time-variant/-invariant components in scenes, subjects’radiance is highly entangled with their own emitted radiance and lighting colors in spatio-temporal domain. In this paper, we present a new effective method to learn disentangled neural fields under the severe illumination changes, named RehearsalNeRF. Our key idea is to leverage scenes captured under stable lighting like rehearsal stages, easily taken before dynamic illumination occurs, to enforce geometric consistency between the different lighting conditions. In particular, RehearsalNeRF employs a learnable vector for lighting effects which represents illumination colors in a temporal dimension and is used to disentangle projected light colors from scene radiance. Furthermore, our RehearsalNeRF is also able to reconstruct the neural fields of dynamic objects by simply adopting off-theshelf interactive masks. To decouple the dynamic objects, we propose a new regularization leveraging optical flow, which provides coarse supervision for the color disentanglement. We demonstrate the effectiveness of RehearsalNeRF by showing robust performances on novel view synthesis and scene editing under dynamic illumination conditions. Our source code and video datasets will be publicly available. Project Page: [https://wcy199705.github.io/RehearsalNeRF](https://wcy199705.github.io/RehearsalNeRF)  \n1  \n1 Introduction  \nNeural Radiance Fields (NeRFs) (Mildenhall et al, 2020) represent a scene as neural implicit functions and enable to render photo-realistic images from arbitrary viewpoints. For wider applicability of NeRFs, their variant representations for dynamic motions (Wu et al, 2022; Zhang et al, 2023; Park et al, 2021a,b; Li et al, 2021; Pumarola et al, 2021; Weng et al, 2022; Peng et al, 2021) have been actively studied. Existing dynamic radiance fields synthesize sequential frames with novel viewpoints by decoupling static and dynamic objects (Wu et al, 2022; Zhang et al, 2023), topological deformation (Park et al, 2021a,b; Li et al, 2021; Pumarola et al, 2021), and human movements (Weng et al, 2022; Peng et al, 2021) . It is worth noting that the word,‘dynamic’, refers subjects’ motions only. In this work, we extend the definition of the ‘dynamic’ to varying illuminations as well as subjects’ motions during taking an input video.  \nEstimating and manipulating scene illuminations, such as intrinsic image decomposition (Barrow et al, 1978; Horn, 1974), relighting (Debevec et al, 2000; Xu et al, 2018) and shape-from-shading (Zhang et al, 1999), has been considered as one of classical research issues. There is a common assumption in these works that light sources are stable and predictable. Nevertheless, the main challenge of them is that the solution isnot unique due to limited image resolution, noise and inaccurate camera geometry. To alleviate the challenges, proper prior information, such as depth geometry (Chen and Koltun, 2013; El Helou et al, 2021; Maier et al, 2017), l","cbCaikp3mffil0TT","https://ap.wps.com/l/cbCaikp3mffil0TT","pdf",5376539,5,1,31,"English","en",105,"# Abstract\n# Introduction\n## Background on NeRFs and dynamic variants\n## Classical illumination estimation and its limitations\n## Illumination-radiance ambiguity in dynamic NeRFs\n## Core idea: rehearsal-stage prior for disentanglement\n# Method overview","[{\"question\":\"How are dynamic objects and lighting colors separated in the method?\",\"answer\":\"RehearsalNeRF uses a learnable temporal vector for lighting effects to disentangle projected light colors from scene radiance, reconstructing dynamic objects through off-the-shelf interactive masks and using optical-flow regularization for coarse supervision of color disentanglement.\"}]",1784174912,78,{"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":79,"head_meta":81,"extra_data":83,"updated_unix":28},"rehearsalnerf-decoupling-intrinsic-neural-fields-of-dynamic-illuminations-for-scene-editing","",{"@graph":36,"@context":78},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/rehearsalnerf-decoupling-intrinsic-neural-fields-of-dynamic-illuminations-for-scene-editing/81624/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"How are dynamic objects and lighting colors separated in the method?","Question",{"text":76,"@type":77},"RehearsalNeRF uses a learnable temporal vector for lighting effects to disentangle projected light colors from scene radiance, reconstructing dynamic objects through off-the-shelf interactive masks and using optical-flow regularization for coarse supervision of color disentanglement.","Answer","https://schema.org",{"og:url":52,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":85},[86,90,94,98,102,107,112,115,120,123,127],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":20,"slug":130},19,"General","general"]