[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-148671-105":59,"doc-detail-148671-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","wildrayzer-self-supervised-large-view-synthesis-in-dynamic-environments","WildRayZer - Self-supervised Large View Synthesis in Dynamic Environments","","WildRayZer提出一种用于动态环境的自监督新视角合成框架：相机与场景中物体同时运动时，静态多视一致性假设会被破坏，进而引发鬼影、幻构几何以及姿态不稳定。方法采用分析-合成策略，先用仅相机静态渲染器解释刚性结构，再利用渲染残差定位瞬态区域；由残差构造伪运动掩码，蒸馏运动估计器，并据此对输入token建模与对损失梯度进行门控，使监督聚焦于跨视角背景补全。同时构建D-RE10K与D-RE10K-iPhone用于大规模训练与评测，实验表明在瞬态去除与全帧合成质量上均优于优化与前馈基线。",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/wildrayzer-self-supervised-large-view-synthesis-in-dynamic-environments/148671/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/wildrayzer-self-supervised-large-view-synthesis-in-dynamic-environments/148671.png","ImageObject",300,407,{"name":92,"@type":93},"Kyle","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-18","2026-08-26",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"WildRayZer如何在缺少动态掩码监督的情况下定位动态区域？","Question",{"text":113,"@type":114},"它采用分析-合成策略：用静态相机渲染器预测刚性结构，并通过渲染误差残差结合DINOv3特征与SSIM来识别偏差区域，从而构造伪运动掩码并蒸馏运动估计器。","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"该方法如何利用伪运动掩码训练模型并提升跨视角背景补全？",{"text":118,"@type":114},"伪运动掩码被用于对输入token进行mask，并对损失梯度进行门控，使监督主要作用在跨视角的背景一致区域，减少动态物体带来的干扰。",{"name":120,"@type":111,"acceptedAnswer":121},"WildRayZer如何进行大规模训练与评测？",{"text":122,"@type":114},"作者构建Dynamic RealEstate10K（D-RE10K）与配对的D-RE10K-iPhone，分别提供包含移动相机与移动物体的真实动态序列以及瞬态-干净视角基准，用于系统评估与定量对比。","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},148671,1787782859,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},3985741905716,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","This CVPR paper is the Open Access version, provided by the Computer Vision Foundation.  \nExcept for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.  \nWildRayZer: Self-supervised Large View Synthesis in Dynamic Environments  \nXuweiyi Chen, Wentao Zhou, Zezhou Cheng  \nUniversity of Virginia  \n[https://wild-rayzer.cs.virginia.edu/](https://wild-rayzer.cs.virginia.edu/)  \nAbstract  \nWe present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments, where both the camera and objects move. Dynamic content breaks the multi-view consistency that static NVS models rely on, causing ghosting, hallucinated geometry, and unstable pose estimation. WildRayZer addresses this by performing an analysis-by-synthesis test: a camera-only static renderer explains rigid structure, and its residuals reveal transient regions. From these residuals, we construct pseudo motion masks, distill a motion estimator, and use it to mask input tokens and gate loss gradients so supervision focuses on cross-view background completion. To enable large-scale training and evaluation, we curate Dynamic RealEstate10K (D-RE10K), a real-world dataset of 15K casually captured dynamic sequences, and D-RE10K-iPhone, a paired transient and clean benchmark for sparse-view transient-aware NVS. Experiments show that WildRayZer consistently outperforms optimization-based and feed-forward baselines in both transient-region removal and full-frame NVS quality with a single feed-forward pass.  \n1. Introduction  \nSelf-supervised learning from large-scale unlabeled data with minimal handcrafted inductive bias has driven major advances in LLMs [31, 57] and visual understanding [18, 49] and generation [53] . A similar trend is only beginning to emerge in 3D vision. While recent 3D models achieve strong performance [20, 80, 83], they often rely on accurate 3D annotations such as point maps and camera poses, or on explicit 3D inductive biases in representations such as NeRF [46] and 3D Gaussian Splatting [32] . These requirements limit scalability, robustness in dynamic environments, and out-of-distribution generalization.  \nMotivated by this, recent work has explored reducing or removing explicit 3D supervision or inductive bias. For example, LVSM [29] proposes a transformer-based view synthesis model with minimal 3D inductive bias. NoPoSplat [92] eliminates the need for camera pose at inference;  \nTarget Pose  \nStatic Views Novel Views  \n(a) RayZer: Self-supervised Large View Synthesis in Static Environments  \n(b) WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments Figure 1 . Our self-supervised WildRayZer learns to render static novel views from dynamic images without any 3D or GT mask supervision. It extends the state-of-the-art self-supervised large view synthesis model RayZer to dynamic environments by adding a learned motion mask estimator and a masked 3D scene encoder.  \nSPFSplat [22] and Splatt3R [71] removes pose supervision during training. Building on LVSM, RayZer [27] introduces a self-supervised framework for sparse-view novel view synthesis that does not require any 3D supervision.  \nDespite recent progress [47, 98], prior work still relies on a fundamental assumption: the 3D scene is static, as illustrated in Figure 1(a) . These models require static inputs during both training and inference, yet real-world 3D environments are inherently dynamic. As a result, existing methods rely on static scene datasets such as RealEstate10K [100], which restricts scalability and prevents full use of abundant in the wild videos with natural dynamic content.  \nIn this work, we propose WildRayZer, a self-supervised learning framework for novel view synthesis in dynamic environments given sparse unposed views as input. Similar to prior efforts that adapt NeRF and 3DGS to in-the-wild settings [33, 45, 64, 89, 99], WildRayZer extends RayZer to dyna","cbCaiinWJpYu9wM8","https://ap.wps.com/l/cbCaiinWJpYu9wM8","pdf",1978515,13,"English","# Introduction\n## Problem setting: dynamic environments for NVS\n## Method: analysis-by-synthesis and pseudo motion masks\n## Training and evaluation: D-RE10K datasets\n## Results and comparison","[{\"question\":\"WildRayZer如何在缺少动态掩码监督的情况下定位动态区域？\",\"answer\":\"它采用分析-合成策略：用静态相机渲染器预测刚性结构，并通过渲染误差残差结合DINOv3特征与SSIM来识别偏差区域，从而构造伪运动掩码并蒸馏运动估计器。\"},{\"question\":\"该方法如何利用伪运动掩码训练模型并提升跨视角背景补全？\",\"answer\":\"伪运动掩码被用于对输入token进行mask，并对损失梯度进行门控，使监督主要作用在跨视角的背景一致区域，减少动态物体带来的干扰。\"},{\"question\":\"WildRayZer如何进行大规模训练与评测？\",\"answer\":\"作者构建Dynamic RealEstate10K（D-RE10K）与配对的D-RE10K-iPhone，分别提供包含移动相机与移动物体的真实动态序列以及瞬态-干净视角基准，用于系统评估与定量对比。\"}]","WildRayZer - Self-supervised Large View Synthesis in Dynamic Environments | PDF",33]