Towards Accurate Human Motion Prediction via Iterative Refinement

8 May 2023  ·  Jiarui Sun, Girish Chowdhary ·

Human motion prediction aims to forecast an upcoming pose sequence given a past human motion trajectory. To address the problem, in this work we propose FreqMRN, a human motion prediction framework that takes into account both the kinematic structure of the human body and the temporal smoothness nature of motion. Specifically, FreqMRN first generates a fixed-size motion history summary using a motion attention module, which helps avoid inaccurate motion predictions due to excessively long motion inputs. Then, supervised by the proposed spatial-temporal-aware, velocity-aware and global-smoothness-aware losses, FreqMRN iteratively refines the predicted motion though the proposed motion refinement module, which converts motion representations back and forth between pose space and frequency space. We evaluate FreqMRN on several standard benchmark datasets, including Human3.6M, AMASS and 3DPW. Experimental results demonstrate that FreqMRN outperforms previous methods by large margins for both short-term and long-term predictions, while demonstrating superior robustness.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human Pose Forecasting 3DPW Sun et al. Average MPJPE (mm) 1000 msec 71 # 2
Human Pose Forecasting AMASS Sun et al. Average MPJPE (mm) 1000 msec 65.4 # 3
Human Pose Forecasting Human3.6M Sun et al. Average MPJPE (mm) @ 1000 ms 109.2 # 6
Average MPJPE (mm) @ 400ms 55.5 # 6

Methods


No methods listed for this paper. Add relevant methods here