arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04573cs.CV
收藏

基于时空可分的图卷积网络姿态预测

Space-Time-Separable Graph Convolutional Network for Pose Forecasting

Sapienza University of Rome(罗马大学)

Theodoros Sofianos, Alessio Sampieri, Luca Franco, Fabio Galasso

摘要:

人体姿态预测是一个复杂的结构化数据序列建模任务,由于其众多的潜在应用,已受到越来越多的关注。研究主要针对时间维的时间序列和人体关节的相互作用与运动树或图形。这使得这两个方面脱钩,并利用了相关领域的进展,但它也限制了对人类姿势的复杂结构关节时空动力学的理解。在这里,我们提出了一种新的时空可分离的图卷积网络(STS-GCN)的姿态预测。STS-GCN第一次只使用图卷积网络(GCN)对人体姿态动态进行建模,在单个图框架内包括时间演化和空间联合交互,这允许运动和空间相关性的串扰。同时,STS-GCN是第一个时空可分离的GCN:时空图的连通性被分解为空间和时间亲和矩阵,这限制了时空串扰,同时实现了完全的联合-联合和时间-时间相关。两个亲和矩阵都是端到端学习的,这导致连接基本上偏离标准运动树和线性时间序列。在对三个复杂的、最新的和大规模的基准测试(Human3.6M [Ionescu et al. TPAMI'14]、AMASS [Mahmood et al. ICCV'19]和3DPW [Von Marcard et al. ECCV'18])的实验评估中,STS-GCN的表现优于最先进的技术,在最困难的长期预测中,平均超过当前最好的技术[Mao et al. ECCV'20] 32%以上,而仅需要其参数的1.7%。我们定性地解释了结果,并说明了图的相互作用的因子联合联合和时间-时间学习图连接。我们的源代码可在以下网址获得:https://github.com/FraLuca/STSGCN

英文摘要:

Human pose forecasting is a complex structured-data sequence-modelling task, which has received increasing attention, also due to numerous potential applications. Research has mainly addressed the temporal dimension as time series and the interaction of human body joints with a kinematic tree or by a graph. This has decoupled the two aspects and leveraged progress from the relevant fields, but it has also limited the understanding of the complex structural joint spatio-temporal dynamics of the human pose. Here we propose a novel Space-Time-Separable Graph Convolutional Network (STS-GCN) for pose forecasting. For the first time, STS-GCN models the human pose dynamics only with a graph convolutional network (GCN), including the temporal evolution and the spatial joint interaction within a single-graph framework, which allows the cross-talk of motion and spatial correlations. Concurrently, STS-GCN is the first space-time-separable GCN: the space-time graph connectivity is factored into space and time affinity matrices, which bottlenecks the space-time cross-talk, while enabling full joint-joint and time-time correlations. Both affinity matrices are learnt end-to-end, which results in connections substantially deviating from the standard kinematic tree and the linear-time time series. In experimental evaluation on three complex, recent and large-scale benchmarks, Human3.6M [Ionescu et al. TPAMI'14], AMASS [Mahmood et al. ICCV'19] and 3DPW [Von Marcard et al. ECCV'18], STS-GCN outperforms the state-of-the-art, surpassing the current best technique [Mao et al. ECCV'20] by over 32% in average at the most difficult long-term predictions, while only requiring 1.7% of its parameters. We explain the results qualitatively and illustrate the graph interactions by the factored joint-joint and time-time learnt graph connections. Our source code is available at: https://github.com/FraLuca/STSGCN

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。

↑