Niantic Spatial 🌎

Today, Niantic Spatial introduces Scaniverse — our flagship product and the gateway to our spatial intelligence platform and Large Geospatial Model. Here’s what’s new: 🔹Scaniverse (iOS mobile + web): Capture once, generate multiple outputs—VPS maps, meshes, and Gaussian splats (Android coming soon) 🔹Collaborative mapping: Multi-user scans fused into a single, continuously improving model 🔹 On-device validation: Preview VPS coverage and test localization in real time 🔹VPS 2.0: Global-scale positioning—centimeter-accurate where mapped, reliable everywhere else (even where GPS fails) 🔹NSDK 4.0 (coming soon): A unified SDK across Unity, Swift, Android, and ROS 2 Read more: hubs.ly/Q049Tpkb0 #NianticSpatial #Scaniverse #VPS #GeospatialAI #AI

🚀 Scaniverse now supports Android enterprise cloud features including cloud-processed splats + meshes, multi-user Sites, and NSDK integration for VPS experiences. SPZ4 also brings 3–5x faster compression and up to 20x faster browser performance. Plus, new 360° camera workflows with Insta360 X4/X5 make high-quality spatial capture faster than ever. 🔗Sign-up for Scaniverse today: hubs.ly/Q04gj47w0 🔗Android version: hubs.ly/Q04gj2r20 #NianticSpatial #Scaniverse #VPS #GeospatialAI #AI #GaussianSplat #Reconstruction #PhysicalAI

(5/5) Led by Niantic Spatial interns Ruijia Chen and Yuheng Wu, with an incredible team behind them. Presented at CHI 2026.

GPS told you that you're 3 metres away. But which direction? For blind and low vision people, that gap is the difference between arriving and not arriving. We built NaviNote to close it. 🏆 CHI 2026 Honourable Mention - top 5% of thousands of submissions. Read blog: hubs.ly/Q04g9Hh70 #NianticSpatial #GeospatialAI #AI #PhysicalAI #VPS Thread 👇(1/5)

(4/5) The results: 88% of participants reached their destination with NaviNote. With standard GPS navigation: 38%. And all 18 participants independently authored their own spatial annotations during the session.

(3/5) Users can also ask what's around them in natural language, hear annotations left by others, and create their own — just by speaking. Notes are pinned to exact 3D locations. In our study, participants created annotations not just for themselves but for the whole BLV community.

(2/5) NaviNote runs on a smartphone and uses Niantic Spatial's Visual Positioning System - centimeter-level accuracy, not GPS approximation - to give blind and low vision users precise turn-by-turn navigation to specific objects, with an audio compass that gets louder as you face the right direction.

Appreciate the respect 🤝 The future of 3D Gaussian Splatting depends on open, interoperable formats that make high-fidelity spatial data faster, lighter, and easier to use across the ecosystem. Excited to see the community building with SPZ 4. #NianticSpatial #Scaniverse #GaussianSplat #SPZ4 #Reconstruction #GeospatialAI #AI #PhysicalAI #VPS

SPZ 4 is here. 🚀 3–5x faster encoding. 2x faster loading. 20x faster in the browser. Tens of millions of points, no sweat. The "JPG for 3D Gaussian splats" just leveled up. Big thanks to everyone who made this release happen, especially the team at @Adobe. Read more: hubs.ly/Q04fvnx90 #NianticSpatial #Scaniverse #SPZ #GaussianSplat #Reconstruction #PhysicalAI #GeospatialAI #AI #Adobe

at @nianticspatial, we're building the real-world model for physical AI. we believe the next generation of AI will move beyond the screen, into real-world environments where some of the hardest problems need to be solved. with high-fidelity gaussian splats as the foundation – robots, AI agents, & autonomous systems can see, localize, understand, & operate in the environments that matter most.

What does it look like when a robot truly understands where it is in the real world? It starts with Niantic Spatial’s Scaniverse, capturing a real-world environment and reconstructing it into a high-fidelity Gaussian splat. From there, our Robot Adventures demo simulates how VPS could localize a robot within that environment, mirroring 360° video of it navigating the physical space. 🔗Get started with Scaniverse today: hubs.ly/Q04dQmHC0 #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI #Robotics

my colleague david hollin built a demo that simulates how robots can localize where they are in the real world while navigating. this high-fidelity gaussian splat at mount tamalpais was captured in just a few minutes with an insta 360° x5. powered by: @nianticspatial

We’re heading to GEOINT 2026 💫 Stop by our booth for live demos of precise geolocation powering geospatial intelligence in GPS-denied environments. 📅 Book a meeting: hubs.ly/Q04dhc100 #NianticSpatial #GEOINT #USGIF #GeospatialIntelligence #PhysicalAI #Scaniverse #VPS #AI #DefenseTech

Our product team walks through the full journey: Capture → Reconstruct → Localize Scaniverse creates high-fidelity 3D inputs from the real world—built for reconstruction, localization, and semantic understanding. Watch the full YouTube playlist: hubs.ly/Q04d5VYM0 #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

Large venues change daily, but most teams rely on outdated maps. With Scaniverse, scan, capture & reconstruct venues into high-fidelity, georeferenced 3D models. 🏟 Plan venue operations 🦺 Improve safety readiness 🛠 Manage assets over time Turn any venue into a continuously updated live spatial model. Download and try: hubs.ly/Q04cYHkZ0 #NianticSpatial #Scaniverse #GeospatialAI #PhysicalAI #AI #3D #DigitalTwins #Reconstruction

with scaniverse you can also use 360° drones to capture large area scans and process those through our 360° pipeline to generate high-fidelity gaussian splats. this was captured on an Antigravity A1 drone. powered by @nianticspatial

VPS 2.0 Outperforms GPS Alone. Niantic Spatial’s Visual Positioning System (VPS) matches live camera data to a spatial model for precise 6DoF localization—indoors, outdoors, and in complex environments where GPS fails. 🔹 ~10-15cm accuracy in mapped areas 🔹 Works in GPS-denied environments 🔹 Persistent spatial anchors Explore this deep dive to learn how VPS works: hubs.ly/Q04csZsd0 #NianticSpatial #Scaniverse #VPS #GIS #GeospatialAI #GEOINT #PhysicalAI #AI #Robotics

📲💻Capture and scan with Scaniverse, then bring your sites directly into NSDK 4.0. A unified spatial data pipeline connects capture → reconstruction → localization → runtime—so your scans are immediately usable in your XR projects. Build with Unity, Swift, Kotlin, and early ROS2 support, and deploy high-performance experiences across mobile and robotic systems within your existing workflows. 🔗Get started today: hubs.ly/Q04cg-4g0 #NianticSpatial #Scaniverse #NDSK #GeospatialAI #PhysicalAI #AI #XR #VR #Robotics #Unity #Kotlin #Swift

NSDK 4.0 is live 🚀 This update makes building faster and more intuitive, with reworked Swift and Kotlin SDKs, easier setup, and new getting started guides. VPS 2.0 improves real-world localization while on-device playback and simplified auth make testing and iteration smoother. 🔗Get started here: hubs.ly/Q04chWf_0 #NianticSpatial #NSDK #SDK #XR #AR #GeospatialAI #PhysicalAI #Unity #Kotlin #Swift

another high-fidelity gaussian splat my colleague david hollin took in japan recently. captured in 2.5 mins with insta 360° x5 camera. powered by @nianticspatial.

“Do you know where a sidewalk begins and ends?” — a simple question from Niantic Spatial CEO, Inhi Cho Suh, that gets to the heart of what today’s AI is missing. For robots, this isn’t theoretical. To safely navigate something as everyday as a sidewalk, they need to understand boundaries, context, and change in real time. Learn about how Niantic Spatial is building the missing piece in Physical AI. hubs.ly/Q04b_dT70 #NianticSpatial #HumanX #GeospatialAI #Robotics #AI #PhysicalAI