[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85356-en":3,"doc-seo-85356-105":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},85356,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",6,"Technology","ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space","ABot-3DWorld 0 introduces a universal multimodal 3D world model that converts text, images, and video into high-fidelity, explorable 3D environments. A unified Spatial Generative Primitive (SGP) represents space as a compact tuple of a high-quality panorama and a spatial point cloud. Inputs are lifted into SGPs, explored via a planned trajectory, and reconstructed into photorealistic 3D Gaussian Splatting worlds. The pipeline supports rich multimodal recovery and generative completion from minimal prompts, enabling map-native spatial exploration at consumer scale.","arXiv :2607 . 11673v1 [ cs .CV] 13 Jul 2026  \nABot-3DWorld 0: A Universal World Model to ExploreAny 3D Space  \nAMAP CV Lab  \nWe present ABot-3DWorld 0 , a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds. At the heart of our framework is a unified Spatial Generative Primitive (SGP)—a compact tuple of a high-quality panorama anda spatial point cloud that delivers an efficient description of any 3D space. Multimodal inputs are first lifted into this primitive; a 3D-consistent panoramic video generator then explores the primitive along a planned trajectory; finally, our panoramic video reconstruction engine converts the generated video into a clean, photorealistic 3D Gaussian Splatting (3DGS) world. This pipeline covers two regimes: rich inputs (multi-view sets, casual video) are lifted into the SGP through a geometry-rigorous recovery that mirrors the observed scene, while a single image or sentence is completed generatively into a creative world. The result is one low-barrier engine for general 3D content creation that further anchors generated worlds to geographic points of interest, enabling map-native spatial exploration at consumer scale. Experiments show that ABot-3DWorld 0 sets the state of the art among open-source methods and demonstrates stronger scene fidelity than Marble under rich multimodal inputs.  \nOfficial Page: [https://abot-world.amap.com/plaza](https://abot-world.amap.com/plaza)  \nFigure 1 Explorable 3DGS worlds generated by ABot-3DWorld 0 from diverse inputs (text, a single image, multiview photos, or video), spanning indoor, street-level, and aerial scenes, from faithful reconstructions to fantastical creations—all produced by a single unified pipeline.  \n1 Introduction  \nAI-driven 3D content creation is undergoing a progression from objects to worlds. Object-level 3D generation, i.e. synthesizing a single 3D asset from text or a single image via score distillation [1] or native mesh generation, has already spawned multiple commercialized companies and products (e.g. Tripo, Meshy, Tencent Hunyuan3D [2]), validating the efficiency and quality of direct 3D synthesis. Its application scope, however, stops at individual assets. Scene generation directly enables immersive spatial experiences, virtual tourism, and scalable game-world production, and offers substantially greater application value through product forms that object generation alone cannot support. Scaling from an isolated object to a complete, explorable 3D scene dramatically increases spatial complexity and scale, giving rise to two core technical challenges. First, how to efficiently represent a complete space: an object can be fully covered by a single circular sweep, whereas a scene extends from a single room to a streetscape or an entire city block, demanding a compact representation that simultaneously encodes geometric structure and visual appearance. Second, how to efficiently explore that space: the narrow field of view of perspective imagery means that covering a full environment requires a large number of frames, with generation and rendering costs growing sharply as scene scale increases. Additionally, scene-specific phenomena such as sky, water surfaces, and long-range illumination introduce difficulties absent from object capture. These challenges explain why only a handful of systems [3–5] have attempted full 3D scene generation to date.  \nRecent systems such as Marble [6] and HY-World 2.0 [7] have demonstrated that generative models can already transform flat inputs into navigable 3D scenes expressed as neural radiance fields [8], 3D Gaussian Splatting [9], or polygonal meshes, substantially advancing the state of the art. Yet several fundamental technical bottlenecks remain open: (i) multimodal inputs (multi-view images, video) are often processed through cascaded generative conversions that discard the geometric evidence present in the original observations and am","cbCaipyF7NCliJ4u","https://ap.wps.com/l/cbCaipyF7NCliJ4u","pdf",44595381,1,31,"English","en",105,"# Introduction\n## Key challenges in 3D scene generation\n## Proposed ABot-3DWorld 0 pipeline\n## Four-stage architecture\n## Multimodal input to SGP\n## SGP to exploration trajectory\n## Trajectory to 3D-consistent panoramic video","[{\"question\":\"What is ABot-3DWorld 0 designed to do?\",\"answer\":\"ABot-3DWorld 0 is a universal multimodal 3D world model that turns text, images, and video into high-fidelity, explorable 3D worlds expressed with 3D Gaussian Splatting.\"},{\"question\":\"How does the model represent 3D space internally?\",\"answer\":\"It uses a Spatial Generative Primitive (SGP), a compact tuple consisting of a high-quality panorama and a spatial point cloud, which serves as the common representation across input modalities.\"},{\"question\":\"How does ABot-3DWorld 0 handle both rich and minimal inputs?\",\"answer\":\"Rich inputs (multi-view sets and casual video) are lifted into SGPs through geometry-rigorous recovery, while minimal inputs (a single image or sentence) are completed generatively using a DiT-based panorama generator followed by monocular geometry estimation.\"}]",1784202756,78,{"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},"abot-3dworld-0-a-universal-world-model-to-explore-any-3d-space","",{"@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/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/abot-3dworld-0-a-universal-world-model-to-explore-any-3d-space/85356/",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},"What is ABot-3DWorld 0 designed to do?","Question",{"text":75,"@type":76},"ABot-3DWorld 0 is a universal multimodal 3D world model that turns text, images, and video into high-fidelity, explorable 3D worlds expressed with 3D Gaussian Splatting.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the model represent 3D space internally?",{"text":80,"@type":76},"It uses a Spatial Generative Primitive (SGP), a compact tuple consisting of a high-quality panorama and a spatial point cloud, which serves as the common representation across input modalities.",{"name":82,"@type":73,"acceptedAnswer":83},"How does ABot-3DWorld 0 handle both rich and minimal inputs?",{"text":84,"@type":76},"Rich inputs (multi-view sets and casual video) are lifted into SGPs through geometry-rigorous recovery, while minimal inputs (a single image or sentence) are completed generatively using a DiT-based panorama generator followed by monocular geometry estimation.","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},[93,97,101,105,110,113,118,123,128,131,135],{"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":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]