projectsim2026cc-by-4.0
Real-to-Sim YAM Benchmark: authored assets
Sixteen sim-ready 3D object assets reconstructed from photographs for real-to-sim robot manipulation evaluation, with physics properties including mass, friction, and restitution for tabletop tasks.
Downloads113
Why This Matters for Physical AI
This dataset enables reproducible real-to-sim transfer evaluation by providing accurately reconstructed 3D object assets with calibrated physics properties, critical for benchmarking robotic manipulation algorithms across the reality gap.
Technical Profile
- Modalities
- 3d_meshusdpbr_textures
- Environment
- simulationtabletop
- Task Types
- manipulationgraspingpick_and_placestackingpouring
- Data Format
- USD
- Annotation Types
- physics_propertiesmaterial_classificationcollision_geometry
- License
- cc-by-4.0
Access
Need custom 3d_mesh data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack