Category · 16 models
Text or image in, textured 3D mesh out — for games, AR, product viz.
Generative 3D models produce meshes, textures and rigs from a prompt or reference image, slashing the time from concept to playable asset.
Genesis Embodied AI
Generative physics platform for robotics simulation and 4D worlds.
Google DeepMind
Real-time interactive world model from a text prompt.
Autodesk
Generative design and AI across AutoCAD, Revit, Forma and Fusion.
Meta
Segment Anything 3D — reconstructs objects, scenes and human bodies from a single image.
Tsinghua University
Visual data comes in various forms, ranging from small icons of just a few pixels to long videos spanning hours.
University of Southern California
We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations.
Stability AI
We study the problem of single-image 3D object reconstruction.
Google DeepMind
We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds.
World Labs
Fei-Fei Li's World Labs spatial intelligence model that generates explorable 3D worlds from a single image.