Parameterizing Variations of human shapes and motions is a long-standing problem in computer graphics and vision. Most of the existing methods only deal with a specific kind of motion, such as body poses, facial expressions, or hand gestures. We propose PanoMan (sParse locAlized compoNents based mOdel for full huMAn motioNs) to handle shape variation and full-motion across body, face, and hand in a unified framework. Like previous approaches, we factor shape variation into principal components to obtain a human shape space that approximates the shape of arbitrary identity. We then analyze sparse localized components in terms of relative edge length and dihedral angle to capture full motions of body poses, facial expressions, and hand gestures. The final piece of our model is a multilayer perceptron (MLP) that fits the residual between the ground truth and the aforementioned two-level approximation. As an application, we employ the discrete-shell deformation to drive the model to fit sparse constraints such as joint positions and surface feature points. We thoroughly evaluate PanoMan on body, face, and hand motion benchmarks as well as scanned data. The existing skinning-based techniques suffer from joint collapsing when encountering twisting motion of joints. Experiments show that PanoMan can capture all kinds of full human motions with high quality and is easier than the state-of-the-art models in recovering poses with wide joint twisting and complex hand gestures.

中文翻译：

---

PanoMan：基于稀疏局部化组件的全人体运动模型

参数化人体形状和动作的变化是计算机图形和视觉中长期存在的问题。大多数现有方法仅处理特定类型的运动，例如身体姿势、面部表情或手势。我们提出 PanoMan（基于稀疏局部化组件的完整人体运动模型）在统一的框架中处理身体、面部和手部的形状变化和完整运动。像以前的方法一样，我们将形状变化分解为主成分，以获得近似于任意身份形状的人体形状空间。然后，我们根据相对边缘长度和二面角分析稀疏的局部分量，以捕捉身体姿势、面部表情和手势的完整运动。我们模型的最后一部分是一个多层感知器（MLP），它适合地面实况和上述两级近似之间的残差。作为一个应用程序，我们使用离散壳变形来驱动模型以拟合稀疏约束，例如关节位置和表面特征点。我们在身体、面部和手部运动基准以及扫描数据上彻底评估 PanoMan。现有的基于蒙皮的技术在遇到关节扭转运动时会出现关节塌陷。实验表明，PanoMan 可以高质量地捕捉各种完整的人体动作，并且比最先进的模型更容易恢复具有广泛关节扭曲和复杂手势的姿势。我们采用离散壳变形来驱动模型拟合稀疏约束，例如关节位置和表面特征点。我们在身体、面部和手部运动基准以及扫描数据上彻底评估 PanoMan。现有的基于蒙皮的技术在遇到关节扭转运动时会出现关节塌陷。实验表明，PanoMan 可以高质量地捕捉各种完整的人体动作，并且比最先进的模型更容易恢复具有广泛关节扭曲和复杂手势的姿势。我们采用离散壳变形来驱动模型拟合稀疏约束，例如关节位置和表面特征点。我们在身体、面部和手部运动基准以及扫描数据上彻底评估 PanoMan。现有的基于蒙皮的技术在遇到关节扭转运动时会出现关节塌陷。实验表明，PanoMan 可以高质量地捕捉各种完整的人体动作，并且比最先进的模型更容易恢复具有广泛关节扭曲和复杂手势的姿势。