Previous work on predicting or generating 3D human pose sequences regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angles or exponential maps as parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations. QuaterNet represents rotations with quaternions and our loss function performs forward kinematics on a skeleton to penalize absolute position errors instead of angle errors. We investigate both recurrent and convolutional architectures and evaluate on short-term prediction and long-term generation. For the latter, our approach is qualitatively judged as realistic as recent neural strategies from the graphics literature. Our experiments compare quaternions to Euler angles as well as exponential maps and show that only a very short context is required to make reliable future predictions. Finally, we show that the standard evaluation protocol for Human3.6M produces high variance results and we propose a simple solution.

中文翻译：

---

使用基于四元数的神经网络模拟人体运动

先前关于预测或生成 3D 人体姿势序列的工作回归关节旋转或关节位置。前一种策略容易沿运动链累积误差，并且在使用欧拉角或指数映射作为参数化时也容易出现不连续性。后者需要重新投影到骨架约束上，以避免骨骼拉伸和无效配置。这项工作解决了这两个限制。QuaterNet 用四元数表示旋转，我们的损失函数在骨架上执行前向运动学以惩罚绝对位置误差而不是角度误差。我们研究了循环和卷积架构，并评估了短期预测和长期生成。对于后者，我们的方法被定性地判断为与图形文献中最近的神经策略一样现实。我们的实验将四元数与欧拉角以及指数映射进行了比较，并表明只需要非常短的上下文即可做出可靠的未来预测。最后，我们证明了 Human3.6M 的标准评估协议产生了高方差结果，我们提出了一个简单的解决方案。