Splat Labs
Splat Labs is an enterprise cloud platform for 3D reality capture that lets users capture, host, and share immersive Gaussian Splat digital twins in seconds. It makes photorealistic 3D environments viewable on any device, with no software, plugins, or downloads required. Gaussian Splatting renders scenes as millions of tiny 3D Gaussian blobs, each with its own position, color, and opacity, creating a realistic environment that can run at 90+ FPS in a browser. Splat Labs works alongside existing capture workflows, including LiDAR, photogrammetry, drones, and splats from tools such as Postshot, Polycam, XGRIDS, DJI, Luma AI, Kiri Engine, and PortalCam. It turns raw splat files into interactive digital twins your entire team can use: upload once, share instantly, and let anyone explore through one link. Users can measure distances and areas directly inside the 3D scene, generate AI floor plans, redesign spaces with AI virtual staging, compare scans over time with 4D timelines.
Learn more
SuperSplat
SuperSplat is the ultimate tool for editing and optimizing 3D Gaussian splats. Clean up your splats with powerful selection tools wrapped up in an easy-to-use interface. SuperSplat is built on the powerful PlayCanvas engine runtime and the PCUI front-end framework. SuperSplat provides a powerful and lightweight visual editing environment that runs in the browser. There is nothing to download and install. SuperSplat operates on the industry standard PLY file format. Use it with any engine you like. Powered by the PlayCanvas engine, SuperSplat can handle even the heaviest 3D Gaussian Splat scenes with ease. Easily select specific splats for deletion. Translate and rotate your scene. Save to PLY, compressed PLY, or SPLAT formats. 3D Gaussian splatting is an exciting new technique to create photorealistic 3D scenes from photogrammetry. However, a captured 3D Gaussian splat may sometimes require some editing.
Learn more
MeshMap
MeshMap is an open 3D mapping platform designed to accelerate innovation in spatial applications and experiences. Users can contribute to building a comprehensive 3D map of the world by scanning environments using devices like smartphones, drones, or professional equipment, and submitting these scans to MeshMap for rewards. The platform supports various scanning methods, including LiDAR, photogrammetry, and Gaussian splatting, with preferred export formats such as .gltf and .ply files. MeshMap offers a Unity SDK to streamline the creation and publication of extended reality applications, enabling creators to import scans, design content, and share it globally. The platform prioritizes compatibility across devices and platforms, supporting Meta Quest 3 and Magic Leap 2, with plans for future expansions. By fostering a contributor-owned, community-managed mapping network, MeshMap aims to democratize access to high-precision, high-coverage 3D maps.
Learn more
spAItial
SpAItial is an AI platform focused on building and deploying Spatial Foundation Models (SFMs), a new class of generative AI systems designed to create and understand 3D environments with physical realism and spatial awareness. Unlike traditional models that generate pixels or text independently, SpAItial’s technology operates directly on 3D structures, capturing geometry, materials, lighting, and physics from the outset to produce coherent, interactive worlds. Its flagship model, Echo-2, can transform a single image into a fully explorable, photorealistic 3D scene using techniques like Gaussian splatting, enabling users to navigate and render environments in real time. It is built around a physically grounded understanding of space-time, allowing AI to reason about how objects exist, interact, and evolve within an environment rather than producing disconnected outputs. This approach reduces inconsistencies common in traditional generative AI and enables more accurate simulation.
Learn more