ContactPose: A Dataset of Grasps with Object Contact and Hand Pose
This dataset addresses a gap for researchers in computer vision, robotics, and AR/VR by providing multimodal data to improve contact modeling techniques, though it is incremental as it focuses on data collection rather than a new method.
The authors tackled the lack of datasets for hand-object contact modeling by introducing ContactPose, a dataset with 2306 unique grasps of 25 objects, 2.9 million RGB-D images, and paired hand pose and object pose data, revealing relationships between hand pose and contact.
Grasping is natural for humans. However, it involves complex hand configurations and soft tissue deformation that can result in complicated regions of contact between the hand and the object. Understanding and modeling this contact can potentially improve hand models, AR/VR experiences, and robotic grasping. Yet, we currently lack datasets of hand-object contact paired with other data modalities, which is crucial for developing and evaluating contact modeling techniques. We introduce ContactPose, the first dataset of hand-object contact paired with hand pose, object pose, and RGB-D images. ContactPose has 2306 unique grasps of 25 household objects grasped with 2 functional intents by 50 participants, and more than 2.9 M RGB-D grasp images. Analysis of ContactPose data reveals interesting relationships between hand pose and contact. We use this data to rigorously evaluate various data representations, heuristics from the literature, and learning methods for contact modeling. Data, code, and trained models are available at https://contactpose.cc.gatech.edu.