[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82833-en":3,"doc-seo-82833-105":30,"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":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},82833,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","SceneFrom3D Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control","SceneFrom3D addresses geometry-conditioned outdoor 3D scene generation by eliminating the view-scheduling bottleneck in a three-stage pipeline. It automatically schedules anchor views from arbitrary coarse or fine input geometries, building a directed generation graph where nodes are anchor views and edges define interpolation trajectories. It further improves controllability with object-level conditioning using per-object identity images for appearance guidance and region-wise geometry-adherence parameters. Experiments show state-of-the-art quality with controllable object appearance and enforced geometry consistency.","arXiv :2607 .04540v 1 [ cs .GR] 5 Jul 2026  \nSceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control  \nGEONUNG KIM, POSTECH, Republic of Korea JEONGEUN PARK, POSTECH, Republic of Korea NURI RYU, POSTECH, Republic of Korea  \nDI LIU, Meta Reality Labs, United States of America SUNGHYUN CHO, POSTECH, Republic of Korea  \nFig. 1. Overview of SceneFrom3D. Given coarse or fine object geometries with per-object appearance and geometry-adherence conditions, SceneFrom3D generates a 3DGS scene that can be rendered and explored from arbitrary viewpoints.  \nGeometry-conditioned 3D scene generation enables the creation of 3D environments from user-provided geometry, offering direct control over scene structure and object layout. To generate such 3D scenes, current methods commonly adopt a three-stage design that first defines a view schedule, then synthesizes multi-view observations along the scheduled views, and finally reconstructs a 3D representation from the generated images. However, defining the view schedule becomes a major bottleneck for outdoor scenes, where large, unstructured, and unbounded geometry makes it difficult to obtain views that provide sufficient coverage while supporting stable generation. To address this bottleneck, we present SceneFrom3D, a framework that automatically schedules views from outdoor input geometries. SceneFrom3D constructs a directed generation graph whose nodes represent anchor views and whose edges represent interpolation trajectories, defining which views to synthesize, which view pairs to interpolate, and in which order generation should proceed. Beyond automatic view scheduling, SceneFrom3D further improves controllability through object-level conditioning, assigning each object an identity image for appearance guidance and a geometry-adherence parameter for region-wise control over the input geometry. Experiments demonstrate that SceneFrom3D achieves state-of-the-art geometry-conditioned outdoor 3D scene generation, producing high-quality scenes with controllable object appearance and geometry adherence. Project [page: kimgeonung.github.io/SceneFrom3D](page: kimgeonung.github.io/SceneFrom3D).  \nAuthors’ Contact Information: Geonung Kim, POSTECH, Republic of Korea, [k2woong92@postech.ac.kr](k2woong92@postech.ac.kr); Jeongeun Park, POSTECH, Republic of Korea, koyy001@ [postech.ac.kr](postech.ac.kr); Nuri Ryu, POSTECH, Republic of Korea, [ryunuri@postech.ac.kr](ryunuri@postech.ac.kr); Di Liu, Meta Reality Labs, United States of America, [lsn33096@gmail.com](lsn33096@gmail.com); Sunghyun Cho, POSTECH, Republic of Korea, [s.cho@postech.ac.kr](s.cho@postech.ac.kr).  \n1 Introduction  \n3D scene generation aims to synthesize a spatially consistent 3D representation of a scene, typically represented by Neural Radiance Fields (NeRF) [Mildenhall et al. 2021] or 3D Gaussian Splatting (3DGS) [Kerbl et al. 2023]. These representations allow rendering from arbitrary viewpoints while maintaining view consistency, enabling users to navigate and explore the generated scene freely. This capability makes them well-suited for immersive and interactive experiences, leading to broad applications in virtual reality, gaming, simulation, robotics, and autonomous driving.  \nRecent research in 3D scene generation has explored various input modalities, including text prompts [Höllein et al. 2023], images [Shriram et al. 2024], scene graphs [Liu et al. 2025], and geometric conditions [Schult et al. 2024]. Among these, geometric conditions provide explicit spatial priors for scene composition in the form of meshes or semantic layouts. Such conditions significantly reduce the ambiguity of the generated scene, leading to more reliable results while providing users with practical control over the generation process.  \nSince paired data between geometry and high-quality 3D scenes is scarce and difficult to acquire, recent state-of-the-art methods commonly decompose geometry-condi","cbCainpz6o2ansiy","https://ap.wps.com/l/cbCainpz6o2ansiy","pdf",11380389,4,1,18,"English","en",105,"# Introduction\n## 3D Scene Generation Representations\n## Geometry-Conditioned Inputs and Prior Reduction of Ambiguity\n## Three-Stage Pipeline and Its View-Scheduling Bottleneck\n## Proposed SceneFrom3D Framework","[{\"question\":\"What problem does SceneFrom3D target in geometry-conditioned outdoor 3D scene generation?\",\"answer\":\"SceneFrom3D targets the difficulty of automatically defining camera view schedules for outdoor inputs, where geometry is large, unstructured, and unbounded, making stable multi-view coverage hard to obtain.\"},{\"question\":\"How does SceneFrom3D generate the view schedule?\",\"answer\":\"It constructs a directed generation graph with anchor views as nodes and interpolation trajectories as edges, specifying which views to synthesize and how interpolation should proceed.\"},{\"question\":\"What does object-level conditioning add to SceneFrom3D?\",\"answer\":\"It assigns each object an identity image to guide appearance and a geometry-adherence parameter for region-wise control over how closely generated content follows the input geometry.\"}]",1784183278,45,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"scenefrom3d-geometry-conditioned-outdoor-3d-scene-generation-via-view-scheduling-with-object-level-control","",{"@graph":36,"@context":85},[37,53,68],{"@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":20},"https://docshare.wps.com/document/scenefrom3d-geometry-conditioned-outdoor-3d-scene-generation-via-view-scheduling-with-object-level-control/82833/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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},"What problem does SceneFrom3D target in geometry-conditioned outdoor 3D scene generation?","Question",{"text":75,"@type":76},"SceneFrom3D targets the difficulty of automatically defining camera view schedules for outdoor inputs, where geometry is large, unstructured, and unbounded, making stable multi-view coverage hard to obtain.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does SceneFrom3D generate the view schedule?",{"text":80,"@type":76},"It constructs a directed generation graph with anchor views as nodes and interpolation trajectories as edges, specifying which views to synthesize and how interpolation should proceed.",{"name":82,"@type":73,"acceptedAnswer":83},"What does object-level conditioning add to SceneFrom3D?",{"text":84,"@type":76},"It assigns each object an identity image to guide appearance and a geometry-adherence parameter for region-wise control over how closely generated content follows the input geometry.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]