CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction

TL;DR

This paper introduces Contact Potential Field (CPF), a novel explicit contact representation for modeling hand-object interactions, combined with a hybrid learning-fitting framework to improve pose estimation and contact modeling.

Contribution

The paper proposes CPF, a new contact representation, and MIHO, a hybrid framework for joint hand-object pose estimation and contact modeling, advancing the state-of-the-art.

Findings

Achieved state-of-the-art reconstruction metrics on benchmarks.

Produced more physically plausible hand-object poses.

Effective even with severe interpenetration or disjointedness in ground-truth.

Abstract

Modeling the hand-object (HO) interaction not only requires estimation of the HO pose, but also pays attention to the contact due to their interaction. Significant progress has been made in estimating hand and object separately with deep learning methods, simultaneous HO pose estimation and contact modeling has not yet been fully explored. In this paper, we present an explicit contact representation namely Contact Potential Field (CPF), and a learning-fitting hybrid framework namely MIHO to Modeling the Interaction of Hand and Object. In CPF, we treat each contacting HO vertex pair as a spring-mass system. Hence the whole system forms a potential field with minimal elastic energy at the grasp position. Extensive experiments on the two commonly used benchmarks have demonstrated that our method can achieve state-of-the-art in several reconstruction metrics, and allow us to produce more physically plausible HO pose even when the ground-truth exhibits severe interpenetration or disjointedness. Our code is available at https://github.com/lixiny/CPF.