arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.04860cs.CV
收藏

多层次时空预测器指导下的多种人体运动预测

Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors

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

Sirui Xu, Yu-Xiong Wang, Liang-Yan Gui

摘要:

在给定一系列历史姿势的情况下预测不同的人体运动已经受到越来越多的关注。尽管进展迅速,现有的工作捕获的多模态性质的人体运动主要是通过基于似然的采样,其中的模式坍塌已被广泛观察。在本文中,我们提出了一个简单而有效的方法,解开随机采样的代码与一个确定性的可学习的组件命名为锚,以提高样本的精度和多样性。邻近因子被进一步分解为空间锚点和时间锚点,这提供了对时空视差的吸引力可解释的控制。原则上,我们的时空锚点采样(STARS)可以应用于不同的运动预测。在这里,我们提出了一种交互增强的时空图卷积网络(IE-STGCN),其对人类运动的先验知识(例如,大量的实验表明,我们的方法在随机和确定性预测方面都优于现有技术,这表明它是一个统一的框架,用于建模人体运动。我们的代码和预训练模型可以在https://github.com/Sirui-Xu/STARS上找到。

英文摘要:

Predicting diverse human motions given a sequence of historical poses has received increasing attention. Despite rapid progress, existing work captures the multi-modal nature of human motions primarily through likelihood-based sampling, where the mode collapse has been widely observed. In this paper, we propose a simple yet effective approach that disentangles randomly sampled codes with a deterministic learnable component named anchors to promote sample precision and diversity. Anchors are further factorized into spatial anchors and temporal anchors, which provide attractively interpretable control over spatial-temporal disparity. In principle, our spatial-temporal anchor-based sampling (STARS) can be applied to different motion predictors. Here we propose an interaction-enhanced spatial-temporal graph convolutional network (IE-STGCN) that encodes prior knowledge of human motions (e.g., spatial locality), and incorporate the anchors into it. Extensive experiments demonstrate that our approach outperforms state of the art in both stochastic and deterministic prediction, suggesting it as a unified framework for modeling human motions. Our code and pretrained models are available at https://github.com/Sirui-Xu/STARS.

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。

↑