ContactGen: Generative Contact Modeling for Grasp Generation
This work addresses the challenge of realistic hand-object interaction modeling for robotics and computer vision applications, representing an incremental advancement in grasp generation.
The paper tackles the problem of generating diverse and geometrically feasible human grasps for various objects by introducing ContactGen, a novel object-centric contact representation, and demonstrates that their method can produce high-fidelity and diverse grasps.
This paper presents a novel object-centric contact representation ContactGen for hand-object interaction. The ContactGen comprises three components: a contact map indicates the contact location, a part map represents the contact hand part, and a direction map tells the contact direction within each part. Given an input object, we propose a conditional generative model to predict ContactGen and adopt model-based optimization to predict diverse and geometrically feasible grasps. Experimental results demonstrate our method can generate high-fidelity and diverse human grasps for various objects. Project page: https://stevenlsw.github.io/contactgen/