OpenUSD assets for
NVIDIA Omniverse
Generate Omniverse-compatible OpenUSD assets with full SimReady compliance. Physics properties, collision geometry, semantic labels, and material bindings — all automated.
The problem
Why existing workflows fall short.
SimReady compliance is complex
Omniverse SimReady spec requires physics, semantics, materials, and validated USD structure. Meeting the full spec manually is time-consuming.
Digital twin bottleneck
Building digital twins in Omniverse requires thousands of physics-accurate assets. Manual creation doesn't scale.
Cross-app interoperability
Assets need to work across Omniverse apps — Isaac Sim, USD Composer, and third-party connectors. Consistency is hard to maintain.
How Rigyd helps
AI-native infrastructure that automates the hard parts.
Full SimReady compliance
Rigyd outputs pass NVIDIA SimReady Foundation validators with proper USDPhysics schemas, semantic labels, and material bindings.
Scales to thousands of assets
Bulk processing via API lets you convert entire asset libraries to Omniverse-ready OpenUSD. Enterprise plans support high-volume pipelines.
Works with your existing models
Upload .glb, .fbx, or .obj files. No pre-processing needed — Rigyd handles geometry optimization and physics annotation.
cost reduction vs manual USD authoring
SimReady spec compliance on output
saved per 1,000-object simulation project
Build your Omniverse asset library faster
Convert any 3D file to SimReady-compliant OpenUSD in minutes.
Starts at $29/month. 30 credits included.
Frequently asked questions
Do Rigyd assets pass NVIDIA SimReady validation?
Yes. Outputs include the USDPhysics schemas, semantic labels, and material bindings required by the NVIDIA SimReady Foundation spec. Validation is part of the generation pipeline — not a manual post-step.
Can Rigyd process my entire 3D asset library?
Yes. Enterprise plans include API access for bulk conversion, and teams have processed 10,000+ object catalogs through the same pipeline. Each asset produces physics-validated OpenUSD within ~5 minutes.
Does the output work across all Omniverse apps?
Yes. Because Rigyd emits valid OpenUSD with standard USDPhysics schemas, assets work identically in Isaac Sim, USD Composer, and any third-party Omniverse connector without re-export.
Can Rigyd assets be used in Omniverse Replicator for synthetic data generation?
Yes. Replicator needs semantic labels and physics for realistic interactions — exactly what Rigyd outputs. Per-prim SemanticsAPI tags allow Replicator to generate pixel-perfect segmentation masks and 3D bounding boxes automatically. Physics ensures dropped, stacked, or perturbed objects settle into realistic configurations rather than floating or interpenetrating.
How does Rigyd handle Omniverse MaterialX shaders and visual materials?
Rigyd preserves visual material bindings from the source file via UsdShade prims, so PBR maps, base color, normal, roughness, and metallic textures transfer cleanly into Omniverse RTX renderer. PhysicsMaterialAPI (friction, restitution, density) is bound separately so visual and physics materials don't conflict. MaterialX shader networks pass through unchanged. For Omniverse Kit-based applications and custom extensions, the layered USD output means rendering and physics teams can edit independently — visual artists work in the materials layer, simulation engineers in the physics layer, and changes from either side don't collide.
Related reading
In-depth guides on robotics simulation, OpenUSD, and SimReady assets.
21 MAY 2026
Synthetic data generation for computer vision in robotics
Real-world labeled robotics data is expensive and slow to capture. Synthetic data is fast and unlimited — but only useful if the underlying simulation has correct physics, semantic labels, and domain randomization. Here's the complete pipeline.
18 MAY 2026
Digital twin creation pipeline for manufacturing
A factory digital twin needs every object to behave physically, not just render. This is the end-to-end pipeline: CAD intake, BIM merge, physics layer, semantic labeling, simulation runtime — at the asset volumes (10K+ unique SKUs) real factories actually contain.
13 MAY 2026
How to set up mass, friction, and joint properties for robot training
The three pillars of robot physics setup — mass, friction, joints — determine whether your trained policy transfers to real hardware. Here's the calibration target for each, the schemas, and the common mistakes that quietly break training.
Explore more
SimReady for Isaac Sim
OpenUSD assets validated for NVIDIA Isaac Sim
Models for MuJoCo
Physics-accurate assets for robot learning
Assets for Gazebo
Simulation-ready models for ROS 2
Warehouse Simulation
50,000+ SKUs need physics properties
Humanoid Robots
Whole-body interaction training assets
Sim-to-Real Transfer
Close the gap with accurate physics data