Log In Sign Up

MotionAug: Augmentation with Physical Correction for Human Motion Prediction

by   Takahiro Maeda, et al.

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 <>.


Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening

Human motion synthesis is a long-standing problem with various applicati...

Adversarial Imitation Learning with Trajectorial Augmentation and Correction

Deep Imitation Learning requires a large number of expert demonstrations...

Imitation learning for variable speed motion generation over multiple actions

Robot motion generation methods using machine learning have been studied...

Scaling Imitation Learning in Minecraft

Imitation learning is a powerful family of techniques for learning senso...

Recognition and Synthesis of Object Transport Motion

Deep learning typically requires vast numbers of training examples in or...

Exploring Versatile Prior for Human Motion via Motion Frequency Guidance

Prior plays an important role in providing the plausible constraint on h...

Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders

Generating conversational gestures from speech audio is challenging due ...