[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83947-en":3,"doc-seo-83947-105":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},83947,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","SynCity 3000 Bootstrapping Scene-Scale 3D Diffusion","SynCity 3000 is a framework for generating globally coherent 3D scenes with fine-grained layout control from a user prompt. It extends image-to-3D generators to scene scale by adapting the model as a convolutional operator and fine-tuning it on synthetic scene-like data to address 3D scene scarcity. A dimetric view of the entire scene, produced from the prompt, is used with the convolutional generator to create 3D outputs of arbitrary size and complexity, improving over prior 3D scene generation approaches.","arXiv :2607 .05392v 1 [ cs .CV] 6 Jul 2026  \nSynCity 3000  \nBootstrapping Scene-Scale 3D Diffusion  \nPaul Engstler, Iro Laina, Christian Rupprecht, and Andrea Vedaldi  \nVisual Geometry Group, University of Oxford {paule,iro,chrisr,[vedaldi}@robots.ox.ac.uk](vedaldi}@robots.ox.ac.uk)[ ](vedaldi}@robots.ox.ac.uk)[https://research.paulengstler.com/syncity-3k](https://research.paulengstler.com/syncity-3k)  \nAbstract. We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D generators to produce complex 3D assets from a single image, we extend this capability to the scale of entire scenes by adapting the generator to be applicable as a convolutional operator. We achieve this by fine-tuning the model on scene-like data generated by a new synthetic data engine, which we propose to address the scarcity of 3D scene data for training. The convolutional generator is then applied to a dimetric image of the entire scene, generated from the user prompt, resulting in 3D scenes of arbitrary size and complexity. Across diverse prompts and layouts, SynCity 3000 produces large, coherent, and detailed scenes, addressing the shortcomings of prior approaches to 3D scene generation.  \nKeywords: 3D scene generation  \n1 Introduction  \nCreating 3D content for movies, games and simulations is a time-consuming and labor-intensive task that requires skilled artists and designers. Recent models that can produce automatically high-quality 3D assets from text prompts [36, 56, 62, 79], but these are usually limited to single objects. Generating entire 3D scenes would be much more impactful in applications. SynCity [15] has recently demonstrated that off-the-shelf models for image generation and image-based 3D reconstruction of single objects can be repurposed to generate large scenes. By building on off-the-shelf models, SynCity sidesteps the lack of large and diverse 3D scene datasets for training a corresponding generator from scratch. It achieves this by reinterpreting the scene as a grid of tiles, each of which is akinto an object which can be generated semi-independently. While this works, the grid-like structure is clearly visible in the final output.  \nIn this paper, we address this limitation by introducing SynCity 3000 , a two-stage framework for generating large-scale 3D scenes from text prompts (Figs. 1 and 3) . Breaking free from the fixed grid-like structure of SynCity, our approach creates 3D worlds of arbitrary structure and complexity. In the first stage, we generate a 2D image template that defines the appearance and layout of  \n2 P. Engstler et al.  \nFig. 1: Diverse 3D worlds of arbitrary size and complexity are easily created with SynCity 3000 from scratch. Our approach first constructs a visually and semantically coherent 2D template of the entire scene, and then converts it into 3D Gaussian Splats with a fine-tuned two-stage generative diffusion model.  \nthe scene. In the second stage, this template is converted into the final 3D scene. This pipeline operates automatically without manual intervention. Notably, the two stages are independent, allowing any template-like image, including those created by graphic artists, to be used for generating a 3D scene.  \nThe stages require repurposing off-the-shelf models for 2D and 3D generation. This necessitates several innovations, which we summarize next and in Sec. 3.  \nIn the first stage, we prompt an image generator to create a high-resolution 2D template of the scene. The generator is based on latent diffusion and, in order to generate scenes of any extent, we divide the 2D latent space into partially overlapping windows without forcing them to look like square tiles. Optional layout constraints can be introduced to allow fine-grained control of the generated scene. By conditioning on all constraints and averaging their contributions at each step of the image diffusion pro","cbCaiateozgW8IOH","https://ap.wps.com/l/cbCaiateozgW8IOH","pdf",7599271,2,1,30,"English","en",105,"# Introduction\n# Related work\n## Image-based scene generation","[{\"question\":\"How does SynCity 3000 enable scene-scale 3D generation from a text prompt?\",\"answer\":\"It first generates a 2D scene template from the prompt, then converts the template into a 3D scene. The conversion uses an adapted generator operating in a convolutional manner over overlapping windows, enabling arbitrary scene size and complexity.\"},{\"question\":\"What problem does the synthetic data engine solve?\",\"answer\":\"It addresses the scarcity of 3D scene data for training. SynCity 3000 fine-tunes the 3D generator using scene-like data produced procedurally by this new synthetic engine.\"},{\"question\":\"How is layout control achieved in SynCity 3000?\",\"answer\":\"Layout control is incorporated during template generation via optional layout constraints, conditioned during diffusion. In the 3D stage, the template is transformed into 3D representations consistent with the generated layout.\"}]",1784191615,76,{"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},"syncity-3000-bootstrapping-scene-scale-3d-diffusion","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/syncity-3000-bootstrapping-scene-scale-3d-diffusion/83947/",4,{"url":51,"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","2026-07-23","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},"How does SynCity 3000 enable scene-scale 3D generation from a text prompt?","Question",{"text":75,"@type":76},"It first generates a 2D scene template from the prompt, then converts the template into a 3D scene. The conversion uses an adapted generator operating in a convolutional manner over overlapping windows, enabling arbitrary scene size and complexity.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem does the synthetic data engine solve?",{"text":80,"@type":76},"It addresses the scarcity of 3D scene data for training. SynCity 3000 fine-tunes the 3D generator using scene-like data produced procedurally by this new synthetic engine.",{"name":82,"@type":73,"acceptedAnswer":83},"How is layout control achieved in SynCity 3000?",{"text":84,"@type":76},"Layout control is incorporated during template generation via optional layout constraints, conditioned during diffusion. In the 3D stage, the template is transformed into 3D representations consistent with the generated layout.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"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":22,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]