Deep learning for predicting or generating 3D human pose sequences is an active research area. Previous work 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 angle or exponential map parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations. Our recurrent network, QuaterNet, represents rotations with quaternions and our loss function performs forward kinematics on a skeleton to penalize absolute position errors instead of angle errors. On short-term predictions, QuaterNet improves the state-of-the-art quantitatively. For long-term generation, our approach is qualitatively judged as realistic as recent neural strategies from the graphics literature.

翻译：深度学习以预测或生成 3D 人类姿势序列是一个活跃的研究领域。 先前的工作会倒退为联合旋转或联合位置。 以前的策略容易在运动链上出现错误积累, 以及使用 Euler 角度或指数映射参数化时的不连续性。 后者需要重新投射到骨骼限制上, 以避免骨骼延展和无效配置。 这项工作解决了两个限制。 我们的经常性网络 QuaterNet 代表着带有四分的旋转, 我们的损失函数在骨骼上表现前向运动功能, 以惩罚绝对位置错误而不是角错误。 在短期预测中, QuaterNet 改进了最先进的定量参数。 对于长期的一代, 我们的方法在质量上被判断为像从图形文献中得出的最新神经战略一样现实。