论文标题
CPF：学习接触电位字段以建模手动对象相互作用
CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
论文作者
论文摘要
对手动对象（HO）相互作用进行建模不仅需要估计HO姿势，而且还需要注意由于其相互作用而引起的接触。在用深度学习方法分别估算手和对象方面取得了重大进展，尚未充分探索同时的HO姿势估计和接触模型。在本文中，我们提出了一个明确的接触表示形式，即接触电位字段（CPF），以及一个学习拟合的混合框架，即MIHO来建模手和对象的相互作用。在CPF中，我们将每个接触的HO顶点对视为弹簧质量系统。因此，整个系统形成一个潜在的领域，在掌握位置处具有最小的弹性能量。对两个常用基准测试的广泛实验表明，我们的方法可以在几种重建指标中实现最新的实验，即使地面真相表现出严重的跨渗透或不连贯性，也可以使我们能够产生更加物理上合理的HO姿势。我们的代码可在https://github.com/lixiny/cpf上找到。
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.
