ShapeGen generates shape-diverse 3D robotic manipulation demonstrations without simulators by curating a functional shape library and applying a minimal-annotation pipeline for novel, physically plausible data.
Generate, transfer, adapt: Learning functional dexterous grasping from a single human demonstration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ShapeGen: Robotic Data Generation for Category-Level Manipulation
ShapeGen generates shape-diverse 3D robotic manipulation demonstrations without simulators by curating a functional shape library and applying a minimal-annotation pipeline for novel, physically plausible data.