ContactOpt: Optimizing Contact to Improve Grasps

Note: We don't have the ability to review paper

PubDate: Apr 2021

Teams: 1Georgia Institute of Technology, 2Facebook Reality Labs Research, 3Intel Labs

Writers: Patrick Grady, Chengcheng Tang, Christopher D. Twigg, Minh Vo, Samarth Brahmbhatt, Charles C. Kemp

PDF: ContactOpt: Optimizing Contact to Improve Grasps

Abstract

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.

You may also like...

Paper