In this work, we present MotionMixer, an efficient 3D human body pose forecasting model based solely on multi-layer perceptrons (MLPs). MotionMixer learns the spatial-temporal 3D body pose dependencies by sequentially mixing both modalities. Given a stacked sequence of 3D body poses, a spatial-MLP extracts fine grained spatial dependencies of the body joints. The interaction of the body joints over time is then modelled by a temporal MLP. The spatial-temporal mixed features are finally aggregated and decoded to obtain the future motion. To calibrate the influence of each time step in the pose sequence, we make use of squeeze-and-excitation (SE) blocks. We evaluate our approach on Human3.6M, AMASS, and 3DPW datasets using the standard evaluation protocols. For all evaluations, we demonstrate state-of-the-art performance, while having a model with a smaller number of parameters. Our code is available at: https://github.com/MotionMLP/MotionMixer
@article{arxiv.2207.00499,
title = {MotionMixer: MLP-based 3D Human Body Pose Forecasting},
author = {Arij Bouazizi and Adrian Holzbock and Ulrich Kressel and Klaus Dietmayer and Vasileios Belagiannis},
journal= {arXiv preprint arXiv:2207.00499},
year = {2022}
}
Comments
Accepted by IJCAI-ECAI'22 (Oral-Long presentation)