论文标题
GNPM：几何感知神经参数模型
GNPM: Geometric-Aware Neural Parametric Models
论文作者
论文摘要
我们提出了一种学习的参数模型（GNPM），这是一种学习的参数模型，它使用点云上的几何感知体系结构来考虑数据的局部数据，以学习解开形状并构成4D动力学的潜在空间。通过利用周期一致性，可以在训练时估算时间一致的3D变形，而无需在训练时进行密集的对应关系。除了学习致密对应的能力外，GNPM还可以实现潜在空间操作，例如插值和形状/姿势转移。我们在各种衣服的人类数据集上评估了GNPM，并表明它的性能与需要在训练过程中需要密集对应的最先进方法相当。
We propose Geometric Neural Parametric Models (GNPM), a learned parametric model that takes into account the local structure of data to learn disentangled shape and pose latent spaces of 4D dynamics, using a geometric-aware architecture on point clouds. Temporally consistent 3D deformations are estimated without the need for dense correspondences at training time, by exploiting cycle consistency. Besides its ability to learn dense correspondences, GNPMs also enable latent-space manipulations such as interpolation and shape/pose transfer. We evaluate GNPMs on various datasets of clothed humans, and show that it achieves comparable performance to state-of-the-art methods that require dense correspondences during training.
