ContactOpt: Optimizing Contact to Improve Grasps
This work addresses the challenge of enhancing robotic or simulated hand grasps for applications in robotics and computer vision, though it appears incremental as it builds on existing image-based methods.
The paper tackled the problem of improving hand grasps by optimizing hand poses to achieve expected contact with objects, resulting in grasps that better match ground truth contact, have lower kinematic error, and are significantly preferred by human participants.
Physical contact between hands and objects plays a critical role in human grasps. We show that optimizing the pose of a hand to achieve expected contact with an object can improve hand poses inferred via image-based methods. Given a hand mesh and an object mesh, a deep model trained on ground truth contact data infers desirable contact across the surfaces of the meshes. Then, ContactOpt efficiently optimizes the pose of the hand to achieve desirable contact using a differentiable contact model. Notably, our contact model encourages mesh interpenetration to approximate deformable soft tissue in the hand. In our evaluations, our methods result in grasps that better match ground truth contact, have lower kinematic error, and are significantly preferred by human participants. Code and models are available online.