[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82080-en":3,"doc-seo-82080-105":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":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},82080,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting","Indoor scene relighting requires photorealism, precise spatial control of light placement, and strict consistency across viewpoints. Text-prompt diffusion editing can manipulate lighting semantics, but enforcing exact 3D source positions often conflicts with the model’s native generative priors. Lume-Palette introduces a progressive two-stage pipeline: illumination distillation to extract canonical illumination palettes from a pretrained diffusion model, and illumination casting to map user-defined spatial lighting conditions from coarse 3D geometry. An asymmetric multi-view conditioning strategy supports dense, multi-modal inputs efficiently.","Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting  \n[ cs .CV] 9 Jul 2026  \nChenjian Gao 1, Linning Xu 1†, and Tianfan Xue 1 ,2 ,3†  \n1 Multimedia Laboratory, The Chinese University of Hong Kong  \n2 Shanghai AI Laboratory  \n3 CPII under InnoHK  \n{gc025, [tfxue}@ie.cuhk.edu.hk](tfxue}@ie.cuhk.edu.hk) [linningxu@link.cuhk.edu.hk](linningxu@link.cuhk.edu.hk)  \n† Corresponding Authors  \n[https://cjeen.github.io/lumepalette](https://cjeen.github.io/lumepalette)  \nAbstract. Indoor scene relighting demands photorealism, precise spatial control, and strict multi-view consistency. While diffusion-based image editing models enable semantic lighting manipulation via text prompts, enforcing exact 3D light placement often disrupts their generative priors. We propose Lume-Palette, a progressive framework that leverages semantic lighting priors for spatially controllable multi-view indoor relighting. The approach decouples relighting into two stages: (1) illumination distillation, which extracts canonical illumination palettes from a pretrained diffusion model to preserve realistic material–light interactions, and (2) illumination casting, which explicitly maps target spatial lighting conditions defined from coarse 3D geometry. To efficiently handle dense multi-view and multi-modal inputs, we introduce an asymmetric multi-view conditioning strategy that selectively injects essential spatial context. Experiments on diverse synthetic scenes and real-world scenes demonstrate that Lume-Palette produces photorealistic, spatially controllable, and multi-view consistent relighting results.  \n2 C. Gao et al.  \nFig. 1: Multi-view indoor scene relighting with Lume-Palette. Our progressive framework first extracts canonical \"illumination palettes\" from multi-view source images to capture material-light interactions. These palettes subsequently guide the synthesis of photorealistic, multi-view consistent relit images under new target illuminations.  \nRecently, diffusion-based image editing models [3, 26, 62] have excelled at manipulating lighting effects via text prompts, yielding photorealistic results. However, text-driven control lacks explicit spatial control over light sources and struggles to preserve consistency when the viewpoint shifts. To achieve spatial lighting control and multi-view consistency, recent approaches [30, 35] attempt to fine-tune diffusion models to accept spatial condition maps. Forcing models to accommodate these invasive spatial constraints from scratch by relying on synthetic data can disturb their generative priors. Consequently, while these approaches achieve spatial alignment, they tend to produce synthetic artifacts, failing to balance precise illumination controllability with natural realism.  \nOur goal is to achieve explicit spatial control for multi-view consistent relighting without losing the diffusion model’s native lighting prior. Drawing inspiration from photometric stereo [11, 16], which reveals material properties by capturing a scene under a set of canonical lighting directions, we propose Lume-Palette, a progressive framework that decouples the relighting process into illumination distillation and illumination casting. Since pre-trained diffusion models are not natively trained to condition on explicit spatial lighting maps, forcing them to condition on this foreign modality requires learning a complex geometry-toappearance mapping from scratch. This heavy adaptation inevitably disrupts the model’s well-tuned generative priors, degrading photorealism. To bypass this, we first distill canonical \"illumination palettes\" via text prompts—a modality the model is inherently aligned with—preserving authentic material responses. These high-quality references then allow the casting stage to focus solely on spatial distribution guided by the geometric conditions. Directionally relit images have also been used by Poirier-Ginter et al. [48] as priors for per-scene relightable rad","cbCaif02AXwYCcei","https://ap.wps.com/l/cbCaif02AXwYCcei","pdf",4972684,1,20,"English","en",105,"# Abstract\n# Illumination Distillation\n# Illumination Casting\n# Multi-View Conditioning Strategy","[{\"question\":\"为什么直接用文本驱动的扩散编辑难以实现精确的空间光源控制与多视角一致性？\",\"answer\":\"文本控制缺少对光源空间位置的显式约束，且在视角变化时容易破坏一致性。强行引入显式空间条件往往会干扰扩散模型原有的生成先验，影响真实感。\"},{\"question\":\"Lume-Palette将重照明解耦成哪两个阶段？各自解决什么问题？\",\"answer\":\"第一阶段是illumination distillation，用于从预训练扩散模型中提取可反映材质-光照交互的规范“illumination palettes”。第二阶段是illumination casting，利用来自粗3D几何的空间目标光照条件生成目标重照明结果。\"},{\"question\":\"illumination casting如何实现用户对虚拟光源的空间摆放并保证跨视角一致？\",\"answer\":\"用户可在重建的粗3D网格中自由放置虚拟光源，网络根据几何条件渲染场景对目标光照的响应。接收者中心的光照条件设计能自然适配离屏光源，同时维持跨视角的3D一致性。\"}]",1784178103,50,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"decoupled-illumination-priors-for-spatially-controllable-multi-view-indoor-scene-relighting","",{"@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/decoupled-illumination-priors-for-spatially-controllable-multi-view-indoor-scene-relighting/82080/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"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","2026-07-17","2026-07-16",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},"为什么直接用文本驱动的扩散编辑难以实现精确的空间光源控制与多视角一致性？","Question",{"text":75,"@type":76},"文本控制缺少对光源空间位置的显式约束，且在视角变化时容易破坏一致性。强行引入显式空间条件往往会干扰扩散模型原有的生成先验，影响真实感。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Lume-Palette将重照明解耦成哪两个阶段？各自解决什么问题？",{"text":80,"@type":76},"第一阶段是illumination distillation，用于从预训练扩散模型中提取可反映材质-光照交互的规范“illumination palettes”。第二阶段是illumination casting，利用来自粗3D几何的空间目标光照条件生成目标重照明结果。",{"name":82,"@type":73,"acceptedAnswer":83},"illumination casting如何实现用户对虚拟光源的空间摆放并保证跨视角一致？",{"text":84,"@type":76},"用户可在重建的粗3D网格中自由放置虚拟光源，网络根据几何条件渲染场景对目标光照的响应。接收者中心的光照条件设计能自然适配离屏光源，同时维持跨视角的3D一致性。","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"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":28,"slug":113},6,"Technology","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":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":21,"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":106,"slug":136},19,"General","general"]