MotionMixer: MLP-based 3D Human Body Pose Forecasting
This addresses the problem of efficient and accurate motion prediction for applications like animation or robotics, though it appears incremental as it builds on existing MLP and attention mechanisms.
The paper tackles 3D human body pose forecasting by proposing MotionMixer, an MLP-based model that sequentially mixes spatial and temporal dependencies, achieving state-of-the-art performance on Human3.6M, AMASS, and 3DPW datasets with fewer parameters.
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