arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.04443cs.CVcs.LG
收藏

通过迭代细化实现精确的人体运动预测

Towards Accurate Human Motion Prediction via Iterative Refinement

University of Illinois at Urbana, Champaign(伊利诺伊大学厄巴纳-香槟分校)

Jiarui Sun, Girish Chowdhary

AI总结:

本文提出FreqMRN框架,结合运动注意力与迭代细化,在姿态和频率空间间转换,利用多损失监督,显著提升短期和长期人体运动预测精度与鲁棒性。

摘要:

人体运动预测旨在根据过去的人体运动轨迹预测未来的姿态序列。为了解决这一问题,本文提出了FreqMRN,一种同时考虑人体运动学结构和运动时间平滑性的人体运动预测框架。具体而言,FreqMRN首先利用运动注意力模块生成固定大小的运动历史摘要,这有助于避免因过长的运动输入而导致的不准确运动预测。然后,在提出的空间-时间感知、速度感知和全局平滑感知损失的监督下,FreqMRN通过提出的运动细化模块迭代地细化预测运动,该模块在姿态空间和频率空间之间来回转换运动表示。我们在多个标准基准数据集上评估了FreqMRN,包括Human3.6M、AMASS和3DPW。实验结果表明,FreqMRN在短期和长期预测方面均大幅优于先前方法,同时展现出卓越的鲁棒性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑