Research method that turns a single photo or video into a simulation-ready 3D scene for robot reinforcement learning.
Updated EU status checked Last shown
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
SimFoundry (also referred to as Sim Factory) is a research project that converts a single photo or video into a physically accurate, simulation-ready 3D scene. The scenes are intended for training robots with reinforcement learning, and the system can generate variations of a scene to diversify training environments.
According to a creator summary, only a paper has been released so far. No official website, code repository, model weights or documentation could be confirmed, and the vendor or authors are not identified in the available material. Details on architecture, benchmarks and licensing are therefore unknown.
It is relevant to robotics researchers working on sim-to-real pipelines who need to build simulated environments from real-world captures without manual 3D modelling.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Turns a single photo or video into a physically accurate, simulation-ready 3D scene for training robots with reinforcement learning, with scene variations. Only a paper is released so far.
Closest neighbours by meaning, not just by category.
Research
Agentic framework that reconstructs sim-ready 3D scenes with rigid, articulated and deformable objects from multi-view RGB.
Research · NVIDIA
NVIDIA dataset of 2,600+ simulation-ready 3D objects with physical properties for robotics and simulation training.
Model
Model that reconstructs a single image into a 3D scene with separate, individually usable objects.
Research
Research framework that turns a single image into a textured 3D asset with articulated parts and physical behavior.
Model
Research model that unifies 3D scene generation and reconstruction in a single pixel-space diffusion model.
Model
Research model that builds complete 3D assets from sparse, unposed images by jointly doing reconstruction and generation.