TLDR: Matthias Niessner, co-founder of the generative AI company Synthesia, has launched a new startup named Spaitial. The Munich-based company aims to revolutionize 3D content creation by developing spatial foundation models capable of generating interactive, photorealistic 3D environments from simple text or image inputs. Spaitial has successfully secured $13 million in seed funding to advance its ambitious vision.
Matthias Niessner, a distinguished figure in the European AI research landscape and co-founder of the $2.1 billion generative AI company Synthesia, has embarked on a new entrepreneurial journey with the launch of Spaitial. The Munich-based startup is set to tackle the next frontier in artificial intelligence: the creation of interactive, photorealistic 3D worlds.
Niessner, currently on an entrepreneurial sabbatical from his role as a professor at the Technical University of Munich (TUM), where he led the visual computing and AI lab for eight years, emphasizes the ambitious scope of his new venture. “We have to think bigger,” Niessner stated, highlighting the significant leap from current AI capabilities in generating static images and videos to building immersive, interactive 3D environments. He added, “We want to create worlds that don’t just look like virtual worlds, they should also behave like virtual worlds. This is an order of magnitude harder than static visualisations.”
Spaitial’s core mission is to develop ‘spatial foundation models’ that can generate complex 3D environments from minimal inputs like text prompts or images. This technology holds immense potential across various sectors, including virtual reality gaming, urban planning, entertainment, digital twinning, robotics, augmented/virtual reality (AR/VR), e-commerce, and autonomous systems. The company aims to make 3D creation accessible and scalable, a stark contrast to the traditionally slow, expensive, and specialized process.
To fuel this ambitious undertaking, Spaitial has successfully raised a $13 million seed round. The funding was led by Earlybird Venture Capital, with participation from Speedinvest and a notable roster of angel investors. These include Robin Rombach (Co-Founder and CEO at Black Forest Labs), Victor Riparbelli (Co-Founder and CEO at Synthesia), Steffen Tjerrild (Co-Founder and COO at Synthesia), and other industry veterans.
The founding team of Spaitial brings a wealth of expertise. Alongside Niessner, the co-founders include Luke Rogers (formerly of McKinsey and Cazoo), Ricardo Martin-Brualla (ex-Google, known for Project Starline and 3D Shopping), and David Novotny (ex-Meta, who led 3D Asset Generation). This combination of academic excellence and commercial acumen positions Spaitial uniquely to lead the ‘Spatial AI revolution.’
Also Read:
- Veterans from Pixar and Apple Launch ‘Intangible’ to Revolutionize Generative AI Video Creation
- Exists Unlocks AI-Powered 3D World Creation for Public Access
While the company has only released a teaser video demonstrating text-to-3D room generation, it has already garnered significant interest. Niessner remains confident in their approach, stating, “I can’t share the full timeline, but it’s not going to be years, and there will also be double steps in between. We know how to do it. We just have to build it.” Spaitial is poised to transform early prototypes into scalable infrastructure and enhance models with advanced physics capabilities, aiming to establish itself as the standard AI-native 3D generation and understanding platform.
