This paper presents a motion data augmentation scheme incorporating motion synthesis encouraging diversity and motion correction imposing physical plausibility. This motion synthesis consists of our modified Variational AutoEncoder (VAE) and Inverse Kinematics (IK). In this VAE, our proposed sampling-near-samples method generates various valid motions even with insufficient training motion data. Our IK-based motion synthesis method allows us to generate a variety of motions semi-automatically. Since these two schemes generate unrealistic artifacts in the synthesized motions, our motion correction rectifies them. This motion correction scheme consists of imitation learning with physics simulation and subsequent motion debiasing. For this imitation learning, we propose the PD-residual force that significantly accelerates the training process. Furthermore, our motion debiasing successfully offsets the motion bias induced by imitation learning to maximize the effect of augmentation. As a result, our method outperforms previous noise-based motion augmentation methods by a large margin on both Recurrent Neural Network-based and Graph Convolutional Network-based human motion prediction models. The code is available at https://github.com/meaten/MotionAug.
翻译:本文介绍了一个运动数据增强计划, 其中包括运动合成, 鼓励多样性 和运动校正, 使物理可信。 运动合成计划包括我们修改的变异自动 Encoder (VAE) 和反虚拟数学(IK)。 在这个VAE中,我们提议的取样近距离抽样方法产生各种有效的动作, 即使没有足够的培训动作数据。 我们基于 IK 的动作合成方法允许我们产生各种运动半自动的半运动。 由于这两个计划在综合动作中产生不切实际的手工艺, 我们的运动校正它们。 这个运动校正计划包括物理模拟的模仿学习和随后的动作去偏移。 为了进行这种模仿学习,我们提议PD- residial 力, 大大加快了培训过程。 此外, 我们的动作去偏移成功地抵消了模拟学习所引发的动作偏向, 以最大限度地扩大增强效果。 结果, 我们的方法比先前的噪音运动增扩增能力方法大幅度了之前的方法, 在基于神经网络的插件和基于图像的变动网络的人的运动预测模型上。 代码可在 https:// gibth/ Mouth. agment.