[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82309-en":3,"doc-seo-82309-105":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},82309,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition","Decomposing outgoing surface radiance into material and illumination during inverse rendering is crucial for relighting and augmented reality, yet the task is highly ill-posed because many combinations yield identical observed color. Multiple lighting captures reduce ambiguity by constraining optimization to correct explanations. This work reconstructs rigidly moving objects to leverage diverse light–surface interactions over time. A relightable pipeline jointly integrates tracking, reconstruction, and inverse rendering for general dynamic objects, improving material accuracy under motion on synthetic and noisy real RGB video data.","Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition  \nRaza Yunus 1 ,3 , Benjamin Ummenhofer2 , Jan Eric Lenssen3 , and Eddy Ilg 1 ,†  \n1 University of Technology Nuremberg  \n2 Intel  \n3 Max Planck Institute for Informatics, Saarland Informatics Campus Project Page: [razayunus.github.io/DIR](razayunus.github.io/DIR). † Now at Google.  \nFig. 1: In contrast to the static multiview setting, where albedo and the corresponding lighting often become entangled, we use the hand-held object capture setting in which diverse surface-light interactions impose strong constraints on the optimization and enable proper material-lighting disentanglement.  \n[ cs .CV]  \narXiv :2607 .09329v1  \nAbstract. Decomposing outgoing surface radiance into material and illumination during inverse rendering is essential for applications such as relighting and augmented reality, yet it is severely ill-posed since multiple combinations can result in the same observed colour. Capturing an object under multiple lighting conditions usually helps resolve this ambiguity as it constrains the optimization towards correct solutions. In this work, we explore the potential of reconstructing rigidly moving objects—which provides observations of diverse light-surface interactions—to resolve the material-lighting ambiguity in inverse rendering. For this purpose, we introduce a relightable approach that marries object tracking and reconstruction with inverse rendering for general rigidly moving objects. Our experimental analysis on synthetic data demonstrates that motion can bean advantage for disentangling material and lighting: the reconstructed material is significantly more accurate when the object is observed under rigid motion than when it is static. Moreover, results on RGB videos of real hand-held objects show that our pipeline preserves this advantage even under noisy real-world conditions.  \nKeywords: Inverse Rendering · 3D Reconstruction · Relighting  \n2 R. Yunus et al.  \n1 Introduction  \nRecent advances in radiance fields have achieved remarkable success in reconstructing scenes with high-fidelity appearance [29,37] and geometry [21,53] . However, these methods typically bake in the appearance under fixed lighting conditions, making them unsuitable for scenarios where relighting is required, e.g. placing reconstructed objects in virtual environments. While inverse rendering approaches estimate material and lighting separately for this purpose [16, 25], the decomposition achieved is often suboptimal due to the inherent ambiguity in inverse rendering. This ambiguity is traditionally resolved by capturing a static object under multiple lighting conditions [25, 33] or utilizing either handcrafted [16] or data-driven [7] priors. However, such methods require extra sophistication, from extended lighting representations for capturing varying lighting conditions [13, 25] to lengthy training procedures for learning useful priors from (limited) 3D data, either for surface materials [7], environment illumination [36] or relighting [41] directly. For most capture settings, a single far-field light representation can provide a decent approximation for the environment illumination. In this work, we posit that if an object is observed and reconstructed while undergoing significant motion, then the evolving light interaction between the object and a single far-field light representation provides enough observations to significantly enhance the material and lighting decomposition.  \nSince the single far-field light assumption requires tracking the object under large pose changes to observe significantly different light interactions, such dynamic reconstruction, while providing stronger constraints for material-lighting ambiguity, also demands accurate tracking, and tracking errors may degrade reconstruction quality. Although category-level or instance-level CAD models have been utilized [56] to track a rigidly-moving object in novel sequences, such methods assu","cbCaislJ9Uv4nnYI","https://ap.wps.com/l/cbCaislJ9Uv4nnYI","pdf",19123007,1,26,"English","en",105,"# Introduction\n## Motivation and problem of ambiguity\n## Dynamic reconstruction and tracking setting\n## Proposed relightable pipeline and optimization stages\n## Evaluation via synthetic dataset","[{\"question\":\"Why is material-lighting decomposition difficult in inverse rendering?\",\"answer\":\"Inverse rendering is ill-posed because multiple material and lighting combinations can produce the same observed surface color, making the decomposition ambiguous.\"},{\"question\":\"How does dynamic (rigid) object motion help resolve this ambiguity?\",\"answer\":\"Observing a rigidly moving object under changing pose produces diverse light–surface interactions, providing stronger constraints for separating material from illumination.\"},{\"question\":\"What are the main components of the proposed relightable approach?\",\"answer\":\"The method uses a three-stage pipeline: progressive sequential optimization with NeuS for coarse geometry and poses, joint optimization with 3D Gaussians for fine geometry and pose, and material optimization via physically based rendering across timesteps.\"}]",1784179528,66,{"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},"dynamic-inverse-rendering-for-enhanced-material-lighting-decomposition","",{"@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/dynamic-inverse-rendering-for-enhanced-material-lighting-decomposition/82309/",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},"Why is material-lighting decomposition difficult in inverse rendering?","Question",{"text":74,"@type":75},"Inverse rendering is ill-posed because multiple material and lighting combinations can produce the same observed surface color, making the decomposition ambiguous.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does dynamic (rigid) object motion help resolve this ambiguity?",{"text":79,"@type":75},"Observing a rigidly moving object under changing pose produces diverse light–surface interactions, providing stronger constraints for separating material from illumination.",{"name":81,"@type":72,"acceptedAnswer":82},"What are the main components of the proposed relightable approach?",{"text":83,"@type":75},"The method uses a three-stage pipeline: progressive sequential optimization with NeuS for coarse geometry and poses, joint optimization with 3D Gaussians for fine geometry and pose, and material optimization via physically based rendering across timesteps.","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"]