CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
This work addresses the problem of simultaneously estimating hand-object pose and modeling contact for researchers working on realistic hand-object interaction, offering an incremental improvement in plausibility.
This paper introduces a Contact Potential Field (CPF) to model hand-object interactions, treating contacting vertex pairs as a spring-mass system. Their MIHO framework achieves state-of-the-art performance on reconstruction metrics and produces more physically plausible hand-object poses, even when ground truth data shows interpenetration or disjointedness.
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.