facebookresearch/ContactPose
A dataset of 2.9M RGB-D grasp images with hand-object contact maps, hand pose, and object pose annotations for computer vision research.
Not currently ranked — collecting fresh signals.
star history
ContactPose is a research dataset and dataloader for hand-object interaction, published at ECCV 2020. It provides synchronized RGB-D images of grasps along with annotated contact maps, 3D hand pose (using the MANO model), and object pose. The repository includes download utilities and Python dataloaders to facilitate training and evaluation of computer vision models for grasp contact prediction and hand pose estimation.
Frequently asked
- What is facebookresearch/ContactPose?
- A dataset of 2.9M RGB-D grasp images with hand-object contact maps, hand pose, and object pose annotations for computer vision research.
- Is ContactPose open source?
- Yes — facebookresearch/ContactPose is open source, released under the MIT license.
- What language is ContactPose written in?
- facebookresearch/ContactPose is primarily written in Jupyter Notebook.
- How popular is ContactPose?
- facebookresearch/ContactPose has 427 stars on GitHub.
- Where can I find ContactPose?
- facebookresearch/ContactPose is on GitHub at https://github.com/facebookresearch/ContactPose.