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.

翻译：给定历史姿态序列预测多样化人体运动已受到越来越多关注。尽管进展迅速，现有工作主要通过基于似然的采样捕捉人体运动的多模态特性，但模式崩塌现象已被广泛观察到。本文提出一种简单而有效的方法，通过将随机采样编码与名为“锚点”的确定性可学习组件解耦，以提升样本精度与多样性。锚点进一步分解为空间锚点与时间锚点，从而对时空差异提供具有吸引力的可解释性控制。原则上，我们的时空锚点采样方法（STARS）可应用于不同运动预测器。本文提出增强交互的时空图卷积网络（IE-STGCN），该网络编码人体运动的先验知识（如空间局部性），并将锚点嵌入其中。大量实验表明，我们的方法在随机预测与确定性预测中均超越现有最优水平，证明其作为人体运动建模的统一框架的有效性。我们的代码与预训练模型已开源至https://github.com/Sirui-Xu/STARS。