Introducing SpAItial: The next dimension in intelligence

We're entering a new era of generative AI -- one where machines do more than understand pixels or words. Today, we're introducing SpAItial: a company built to tackle one of the most complex and consequential challenges in AI -- creating intelligent systems that natively understand and generate 3D worlds. Backed by a world-class team and leading investors, we're setting out to reshape how AI engages with space, time, and reality itself.

SpAItial is pioneering Spatial Foundation Models (SFMs), a new class of AI designed to generate and reason about the appearance and physics of real and imagined environments. SFMs possess an intrinsic understanding of space-time, enabling breakthrough applications at the intersection of virtual and physical worlds.

Unlike existing generative AI technologies -- whether LLMs, image models, or video models -- SFMs operate natively in physical space. That native grounding dramatically advances their cognitive capabilities and more closely mirrors human understanding. SFMs can revolutionize industries ranging from immersive entertainment and CAD to next-generation VR/AR experiences and physically intelligent robotics.

There are clear wins when interactive 3D is available for any kind of visualization. When it is rendered at uncompromising, photorealistic quality, it becomes more engaging, immersive, and faithful than 2D content.

Our mission: Bridging the virtual and physical

At SpAItial, we envision a future where AI effortlessly navigates and connects the virtual and physical realms. Our mission is to build physics-consistent, spatio-temporally grounded AI that understands the 3D world like humans do. Rather than generating pixels, our SFMs operate on 3D structures -- capturing geometry, materiality, and physics from the outset. That foundation allows us to generate photorealistic, physically plausible environments from sparse inputs such as a single image, a short-form video, or even a text description.

From crafting high-fidelity game environments to enabling robots to navigate dynamic spaces, SFMs are designed to power:

• Immersive media and entertainment: Gaming, film, and AR/VR experiences with coherent, photorealistic 3D environments.
• Digital twins and design simulation: Real-time, high-fidelity replicas of physical environments for planning, visualization, and testing.
• Autonomous systems and robotics: Enhanced spatial reasoning, navigation, and interaction in physical spaces.
• Industrial and urban infrastructure: Smarter modeling, automation, and control across construction, logistics, and manufacturing.

Our Team: Research meets real-world application

SpAItial was founded by proven industry leaders and deep-tech veterans who pair cutting-edge academic research with real-world product execution:

• Matthias Niessner - Professor at TU Munich, co-founder of Synthesia, formerly at Stanford.
• Luke Rogers - Formerly at McKinsey and an early leader at Cazoo, helping scale the company from seed to IPO.
• Ricardo Martin-Brualla - Formerly at Google, most recently led generative 3D efforts at Google Shopping and previously ML at Google Beam.
• David Novotny - Formerly at Meta, where he led initiatives in 3D asset generation and digital twinning.

That mix of technical excellence and startup leadership positions us to lead and innovate.

Beyond the founding team, our broader technical staff brings deep expertise across AI research, large foundational models, graphics, and 3D generative AI. Notably, Katja Schwarz, formerly at Meta, pioneered early generative 3D models like GRAF and VoxGRAF, and Mojtaba Bemana, whose X-Fields paper defined 4D neural representations and earned the 2025 EuroGraphics PhD Award. We've assembled a world-class group of builders united by a shared vision -- and we're just getting started.

Backing our vision

We're excited to have secured a $13 million seed round led by Earlybird Venture Capital, with participation from Speedinvest and a group of prominent angel investors. This funding allows us to accelerate model development, scale infrastructure, and expand our team.

Exceptional angels also joined the round, including Robin Rombach (Black Forest Labs), Victor Riparbelli and Steffen Tjerrild (Synthesia), Christian Stiebner, Edward Grefenstette, Maximilian Odendahl (ex-CEO Silexica), Jon Barron, Rahul Garg, Sergej Epp (CISO at Sysdig and Palo Alto Networks), Elias Schneider (Codesphere), Paul Whitehead (Zoopla), and others.

We take their support as validation that we're on the right track -- and we're eager to keep building.

What's next: Scaling and collaboration

We're focused on enhancing the core capabilities of our models, developing the technical foundations required for scalable deployment, and growing our team with exceptional talent across AI, graphics, and 3D systems. At the same time, we're partnering with leading organizations to explore real-world applications and pilot our technology across industries.

We're opening early access to our technology. If you're interested in trying out our models or collaborating with us, join the waitlist and be part of the next wave of spatial AI innovation.

Join us on this journey

We're just beginning to redefine how AI perceives and interacts with the world. If you're passionate about shaping the future of spatial intelligence, we'd love to connect.

Explore Open Roles

A sneak peak

We demonstrate the generation of 3D environments from simple text prompts or images that can be interactively rendered from novel camera viewpoints in a photorealistic fashion. This teaser offers a first glimpse into the capabilities of our early model and our direction of travel.