ContactArt is a dataset for learning hand-object interaction priors for hand and articulated object pose estimation. The dataset is created using visual teleoperation, where the human operator can directly play within a physical simulator to manipulate the articulated objects. All the object models are from Partnet dataset for the convenience of scaling up. ContactArt can provide accurate annotation, rich hand-object interaction, and contact information.
Source: ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses EstimationPaper | Code | Results | Date | Stars |
---|