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/
Cite
@article{arxiv.2310.03740,
title = {ContactGen: Generative Contact Modeling for Grasp Generation},
author = {Shaowei Liu and Yang Zhou and Jimei Yang and Saurabh Gupta and Shenlong Wang},
journal= {arXiv preprint arXiv:2310.03740},
year = {2023}
}
Comments
Accepted to ICCV 2023. Website: https://stevenlsw.github.io/contactgen/