# Niantic Spatial | Niantic Spatial, Inc. > Markdown mirror of DialtoneApp's public top-site detail page for `nianticspatial.com`. URL: https://dialtoneapp.com/top-sites/nianticspatial.com/index.md Canonical HTML: https://dialtoneapp.com/top-sites/nianticspatial.com ## Summary - Domain: `nianticspatial.com` - Website: https://nianticspatial.com - Description: ai readable | score 16 | purchase read only - Label: ai_readable - Payment surface: Not available - Purchase boundary: read_only - Control boundary: unknown - Rank: 20904 ## robots Not found. ## llms ~~~text # Niantic Spatial > Niantic Spatial, Inc. is a geospatial AI company headquartered in San Francisco, CA. We are building a living model of the world that machines and people can talk to - spatial intelligence that enables people, robots, and AI agents to understand and interact with the physical world. Our flagship product is the Large Geospatial Model (LGM), trained on a proprietary database of over 30 billion posed real-world images. ## Company - Founded: 2025 (spun out from Niantic, Inc. following the sale of its games division to Scopely) - CEO & Founder: John Hanke - Headquarters: San Francisco, California, USA - Origin: Built on 25+ years of geospatial AI, mapping, and AR research, originally incubated inside Google - Website: https://www.nianticspatial.com - App: scaniverse.nianticspatial.com/ - Contact: https://www.nianticspatial.com/contact ## What We Do Niantic Spatial provides a three-part geospatial AI platform — Reconstruct, Localize, and Understand — powered by the Large Geospatial Model. Our platform enables: - Creation of high-fidelity, geo-referenced 3D digital twins of physical environments - Centimeter-level, six-degree-of-freedom visual positioning for humans and machines, including in GPS-denied environments - Semantic 3D world querying that allows AI agents, robots, and enterprise systems to ask open-ended questions about real-world spaces ## Core Products - **Scaniverse**: Scaniverse is our self-serve platform for delivering spatial services: An integrated web and mobile platform that powers data capture and upload, generation of spatial assets, inspection of meshes and splats, and localization with VPS.- **Reconstruct**: Fuses multi-sensor inputs into accurate 3D models (Gaussian splats and textured meshes) for simulation, inspection, and planning. https://www.nianticspatial.com/products/reconstruct - **Localize**: Precise visual positioning system (VPS) that now works at global scale – no prior scanning required. In places mapped with Scaniverse, VPS delivers near centimeter-accurate 6DoF localization. Everywhere else, it corrects GPS errors and dropout to provide improved, reliable positioning and heading, especially in GPS degraded environments. https://www.nianticspatial.com/products/localize - **Understand**: Semantic understanding at every 3D point in a geo-referenced map, enabling LLMs and AI agents to query the physical world. https://www.nianticspatial.com/products/understand - **Capture**: Tools and services to acquire high-quality 3D aerial and ground data, including the Scaniverse app and on-demand mapping. https://www.nianticspatial.com/products/capture - **Scaniverse**: Enterprise-grade 3D scanning app for iOS and Android. https://scaniverse.nianticspatial.com/ - **Niantic Spatial Development Kit (NSDK) 4.0**: a unified SDK for Unity, Swift, Android, and ROS 2, connecting directly to Scaniverse and VPS 2.0. ## Large Geospatial Model (LGM) The LGM is Niantic Spatial's foundational AI model. Key facts: - Trained on 30+ billion posed real-world images from ground and overhead sensors - Adds spatial reasoning capabilities to Large Language Models (LLMs) - Delivers per-pixel semantic analysis and tracks 200+ object types - Enables queryable 3D maps — users and machines can ask open-ended spatial questions - Differentiator: Unlike general-purpose LLMs, the LGM is grounded in precise physical-world geometry and semantics - More: https://www.nianticspatial.com/blog/largegeospatialmodel ## Visual Positioning System (VPS) - Industry-leading vision-based positioning used by tens of millions of users - Delivers centimeter-level, 6DoF pose estimation - Works indoors, outdoors, and in GPS-denied environments - Supports robots, AI agents, AR devices, and mobile applications - More: https://www.nianticspatial.com/products/localize ## Enterprise Solutions - **Intelligent Logistics**: Autonomous last-mile and warehouse navigation and verification. https://www.nianticspatial.com/use-cases/intelligent-warehousing-and-logistics - **Spatial Collaboration**: Remote site surveys, risk assessments, and real-time team collaboration across environments. https://www.nianticspatial.com/use-cases/spatial-planning-and-remote-collaboration - **Immersive Experiences**: AR tours, wayfinding, and gamified spatial experiences. https://www.nianticspatial.com/use-cases/immersive-entertainment-and-experiences ## Notable Partnerships - **Coco Robotics**: Joint development of spatial AI for urban autonomous delivery - **Vantor**: Integration for GPS-denied military and industrial operations using visual positioning - **Meow Wolf**: Taking physical exhibitions and into the world of augmented reality - **Aechelon**: Enhancing U.S. Coast Guard training with advanced 3D flight simulation and geospatial AI - **Snap**: Building a next generation AI map that will serve as the foundation for AR glasses and AI agents to understand, navigate and interact with the real world. - **Kojima Productions**: A technology partnership that will leverage geospatial AI technology to bring Hideo Kojima's iconic storytelling into the real world. - **Ubisoft & Sugar Creative**: Using visual positioning to deliver centimeter-level precision that anchors mixed-reality content to the physical world. ## Research Niantic Spatial's research team publishes fundamental work in geospatial AI, computer vision, and spatial computing, collaborating with leading universities. - Research overview: https://www.nianticspatial.com/research - Blog: https://www.nianticspatial.com/blog ## Developer Resources - SDK Documentation: https://www.nianticspatial.com/docs/ - Developer Forums: https://community.nianticspatial.com/ - Developer Partner Program: https://www.nianticspatial.com/partners ## Key Pages for AI Reference - About: https://www.nianticspatial.com/about - Enterprise: https://www.nianticspatial.com/enterprise - Responsible Innovation: https://www.nianticspatial.com/responsible-innovation - Press contact: press@nianticspatial.com ## Do Not Scrape The following sections contain user-generated or session-specific content and are not suitable for LLM training or citation: - /cookies Homepage schema example [ { "@context": "https://schema.org", "@type": "Organization", "name": "Niantic Spatial, Inc.", "url": "https://www.nianticspatial.com", "logo": "https://www.nianticspatial.com/logo.png", "description": "Niantic Spatial builds geospatial AI infrastructure, including a Large Geospatial Model trained on 30 billion posed images, enabling spatial reasoning for LLMs, robots, and AI agents.", "foundingDate": "2025", "founder": { "@type": "Person", "name": "John Hanke" }, "address": { "@type": "PostalAddress", "addressLocality": "San Francisco", "addressRegion": "CA", "addressCountry": "US" }, "contactPoint": { "@type": "ContactPoint", "contactType": "Sales", "url": "https://www.nianticspatial.com/contact" }, "sameAs": [ "https://en.wikipedia.org/wiki/Niantic_Spatial", "https://www.linkedin.com/company/niantic-spatial", "https://twitter.com/nianticspatial" ] }, { "@context": "https://schema.org", "@type": "WebSite", "name": "Niantic Spatial", "url": "https://www.nianticspatial.com", "potentialAction": { "@type": "SearchAction", "target": "https://www.nianticspatial.com/search?q={search_term_string}", "query-input": "required name=search_term_string" } } ] ~~~ ## llms-full Not found.