Building the foundations of interactive worlds that are persistent, multi-agent, and universally authorable — driven by our research in generative 3D and world models.
Open-source 3D Gaussian generator. Unmatched quality, controllable budget, minimal dependency.
Learn more
A versatile open-source model for converting any image to a high-quality 3D mesh.
Learn more
Fast textured mesh generation. No GPU required. Built with Stability.AI.
Learn more
Meet us at Los Angeles Convention Center, CA | July 19–23.Meet us atLos Angeles Convention CenterCA | July 19–23.
Learn MorePixTex performs multi-view diffusion directly in pixel space to generate high-quality, globally consistent textures for 3D assets.
Nexus generates native triangle meshes with diffusion by decoupling vertex generation and topology modeling, avoiding the inefficiency of autoregressive mesh serialization.
Grow3D is an autoregressive 3D shape generation framework that predicts hierarchical octree structures in a coarse-to-fine manner, enabling fast and high-fidelity 3D generation.
TopoCap extracts motion from monocular videos and retargets it to 3D characters with arbitrary skeletal topologies, enabling topology-agnostic video-to-animation.
We pursue first-principles research in 3D, from spatial reasoning and neural graphics to interactive world models. Our work has been consistently recognized at top venues such as SIGGRAPH, CVPR, NeurIPS, and ICCV, and we have open-sourced 30+ projects to advance the broader community.
We offer competitive compensation, ownership of core technical directions, dedicated large-scale compute, and a focused research culture built for long-term, high-impact work.
View All Openings
