The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors -- no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer, and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: https://qitaozhao.github.io/ContextAware-PoseFormer

翻译：当前三维人体姿态估计的主流范式依赖将二维姿态序列提升至三维，其精度提升高度依赖长期时间线索（即需使用大量视频帧），导致性能饱和、计算复杂且存在非因果性问题。这源于此类方法无法感知空间上下文——纯二维关节点坐标不包含视觉信息。为突破该瓶颈，我们提出简洁而有效的解决方案：直接利用现成（预训练）二维姿态检测器产生的中间视觉表征——甚至无需在三维任务上微调。关键发现是：检测器在学习定位二维关节点时，因主干网络的区域操作机制，其表征（如特征图）已隐式编码了以关节点为中心的空间上下文。我们设计了名为Context-Aware PoseFormer的轻量基线方法验证其有效性。无需任何时序信息，本方法在速度和精度上均显著超越其无上下文版本PoseFormer，以及依赖数百帧视频的现有最优方法。项目主页：https://qitaozhao.github.io/ContextAware-PoseFormer