用简单模型统一预测人体运动轨迹和姿态，性能领先。
SimpliHuMoN: Simplifying Human Motion Prediction
- 基于Transformer自注意力机制，统一建模动作空间与时间关系。
- 在Human3.6M等多数据集上，轨迹与姿态预测均达顶尖水平。
- 无需任务调整，一套模型通吃三种预测任务，适合实用部署。
人体运动预测结合了轨迹预测与人体姿态预测两个任务。针对每个任务，已有专用模型，但将二者整合实现整体预测仍具挑战，且现有方法在单任务基准上表现不佳。为此，我们提出一种基于Transformer的简洁高效模型。该模型通过堆叠自注意力模块，有效捕捉单个姿态内的空间依赖性以及运动序列中的时间关系。此简洁、端到端的模型具备足够通用性，无需任务特化即可处理仅姿态、仅轨迹及联合预测任务。在包括Human3.6M、AMASS、ETH-UCY和3DPW在内的多个基准数据集上的大量实验表明，该方法在所有任务上均达到当前最优性能。
原文摘要 · Abstract (English)
Human motion prediction combines the tasks of trajectory forecasting and human pose prediction. For each of the two tasks, specialized models have been developed. Combining these models for holistic human motion prediction is non-trivial, and recent methods have struggled to compete on established benchmarks for individual tasks. To address this, we propose a simple yet effective transformer-based model for human motion prediction. The model employs a stack of self-attention modules to effectively capture both spatial dependencies within a pose and temporal relationships across a motion sequence. This simple, streamlined, end-to-end model is sufficiently versatile to handle pose-only, trajectory-only, and combined prediction tasks without task-specific modifications. We demonstrate that this approach achieves state-of-the-art results across all tasks through extensive experiments on a wide range of benchmark datasets, including Human3.6M, AMASS, ETH-UCY, and 3DPW.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。