SuperSplat

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.

Atlas is a next-generation omni world model for spatial intelligence that natively operates on text, images, video, and 3D. Built as a multimodal autoregressive diffusion transformer, it combines inputs into a shared spatial context and generates what comes next while staying consistent in 3D with everything it has seen and imagining what lies beyond it. Atlas supports world generation, reconstruction, and simulation across a broad range of tasks. It can generate images and videos from one or more reference images with pixel-perfect camera control, producing long, coherent videos with manually designed camera paths. For spatial reconstruction, Atlas can recreate real-world scenes from sparse input images, generate novel views, and produce explicit 3D outputs such as point clouds and 3D Gaussian splats. More input views provide additional context, allowing the model to reduce imagination and create increasingly faithful reconstructions. Atlas also models how worlds evolve over time.