Towards Accurate Human Motion Prediction via Iterative Refinement

TL;DR

This paper introduces FreqMRN, a novel human motion prediction framework that iteratively refines predictions by leveraging frequency and pose space conversions, achieving superior accuracy and robustness on benchmark datasets.

Contribution

The paper presents FreqMRN, a new iterative refinement framework that incorporates frequency domain analysis and specialized loss functions for improved human motion prediction.

Findings

Outperforms previous methods on Human3.6M, AMASS, and 3DPW datasets.

Achieves significant improvements in both short-term and long-term predictions.

Demonstrates robustness across various motion prediction scenarios.

Abstract

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.