Research framework generating simulation-ready 3D assets (rigid, deformable, articulated) with physical properties.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
PhysX-Omni is a research framework for generating simulation-ready physical 3D assets. Unlike many 3D generators that ignore physical properties or handle only one asset type, it covers rigid, deformable and articulated objects in a single framework. It uses a geometry representation designed for vision-language models that encodes high-resolution 3D structure without compression.
The project also introduces PhysXVerse, described as the first general simulation-ready 3D dataset covering diverse indoor and outdoor categories, and PhysX-Bench, a benchmark covering six attributes: geometry, absolute scale, material, affordance, kinematics and function description. The authors report strong results on both generation and understanding, and show applications in simulation-ready scene generation and robotic policy learning. A YouTube creator summary says it outperforms Articulate Anything and PhysX-Anything and that the training script and dataset are open; this was not confirmed on the fetched project page.
It is aimed at embodied AI and physics-based simulation researchers. The provided page lists no vendor, code repository, weights link, license or paper link, so release details are unverified.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
3D generator producing simulation-ready assets with geometry, scale, materials and articulated joints, unifying rigid and articulated objects in one framework. Outperforms Articulate Anything and PhysX-Anything; fully open source with training script and dataset.
Closest neighbours by meaning, not just by category.
Research
Research framework that turns a single image into a textured 3D asset with articulated parts and physical behavior.
Model · NVIDIA
NVIDIA's open omni-model family for physical AI: world simulation, reasoning and action generation for robots and AVs.
Research · NVIDIA
NVIDIA dataset of 2,600+ simulation-ready 3D objects with physical properties for robotics and simulation training.
Model · Hi3D
Open-source image-to-3D and text-to-3D generation model from Hi3D, formerly Sparc3D, trained on ~2M curated 3D assets.
Model · Hao AI Lab
Distilled MiniMax H3 reference-to-video-and-audio model from Hao AI Lab, generating in 8 steps instead of 50.
Model
Diffusion transformer that generates rigid and elastic 3D mesh dynamics in world coordinates from initial velocities and materials.