Single-stage multi-person pose estimation aims to jointly perform human localization and keypoint prediction within a unified framework, offering advantages in inference efficiency and architectural simplicity. Consequently, multi-scale real-time detection architectures, such as YOLO-like models, are widely adopted for real-time pose estimation. However, these approaches typically inherit a box-driven modeling paradigm from object detection, in which pose estimation is implicitly constrained by bounding-box supervision during training. This formulation introduces biases in sample assignment and feature representation, resulting in task misalignment and ultimately limiting pose estimation accuracy. In this work, we revisit box-driven single-stage pose estimation from a keypoint-driven perspective and identify semantic conflicts among parallel objectives as a key source of performance degradation. To address this issue, we propose a keypoint-driven learning paradigm that elevates pose estimation to a primary prediction objective. Specifically, we remove bounding-box prediction and redesign the prediction head to better accommodate the high-dimensional structured representations for pose estimation. We further introduce a keypoint-driven dynamic sample assignment strategy to align training objectives with pose evaluation metrics, enabling dense supervision during training and efficient NMS-free inference. In addition, we propose a smooth OKS-based loss function to stabilize optimization in regression-based pose estimation. Based on these designs, we develop a single-stage multi-person pose estimation framework, termed ER-Pose. On MS COCO and CrowdPose, ER-Pose-n achieves AP improvements of 3.2/6.7 without pre-training and 7.4/4.9 with pre-training respectively compared with the baseline YOLO-Pose. These improvements are achieved with fewer parameters and higher inference efficiency.

翻译：单阶段多人姿态估计旨在统一框架内同时执行人体定位与关键点预测，在推理效率和架构简洁性方面具有优势。因此，多尺度实时检测架构（如类YOLO模型）被广泛用于实时姿态估计。然而，这些方法通常延续了目标检测中的框驱动建模范式，在训练过程中姿态估计隐式受到边界框监督的约束。这种范式在样本分配和特征表示中引入偏差，导致任务错位并最终限制姿态估计精度。本研究从关键点驱动视角重新审视框驱动单阶段姿态估计，发现并行目标间的语义冲突是性能下降的关键原因。为解决该问题，我们提出一种关键点驱动的学习范式，将姿态估计提升为主要预测目标。具体而言，我们移除边界框预测并重新设计预测头，以更好地适应姿态估计所需的高维结构化表示。进一步提出关键点驱动的动态样本分配策略，使训练目标与姿态评估指标对齐，实现训练期间的密集监督和无需NMS的高效推理。此外，我们提出基于平滑OKS的损失函数，以稳定基于回归的姿态估计优化过程。基于这些设计，我们构建了名为ER-Pose的单阶段多人姿态估计框架。在MS COCO和CrowdPose数据集上，ER-Pose-n相较于基线YOLO-Pose，在无预训练情况下分别实现3.2/6.7的AP提升，在有预训练情况下分别实现7.4/4.9的AP提升。这些改进是在参数更少且推理效率更高的条件下实现的。