Most 2D human pose estimation benchmarks are nearly saturated, with the exception of crowded scenes. We introduce PMPose, a top-down 2D pose estimator that incorporates the probabilistic formulation and the mask-conditioning. PMPose improves crowded pose estimation without sacrificing performance on standard scenes. Building on this, we present BBoxMaskPose v2 (BMPv2) integrating PMPose and an enhanced SAM-based mask refinement module. BMPv2 surpasses state-of-the-art by 1.5 average precision (AP) points on COCO and 6 AP points on OCHuman, becoming the first method to exceed 50 AP on OCHuman. We demonstrate that BMP's 2D prompting of 3D model improves 3D pose estimation in crowded scenes and that advances in 2D pose quality directly benefit 3D estimation. Results on the new OCHuman-Pose dataset show that multi-person performance is more affected by pose prediction accuracy than by detection. The code, models, and data are available on https://MiraPurkrabek.github.io/BBox-Mask-Pose/.

翻译：大多数二维人体姿态估计基准已接近饱和，拥挤场景除外。我们提出了PMPose，一种融合了概率化表述与掩码条件化的自上而下二维姿态估计器。PMPose在不牺牲标准场景性能的前提下，提升了拥挤场景下的姿态估计效果。在此基础上，我们提出了BBoxMaskPose v2（BMPv2），它集成了PMPose与一个增强的基于SAM的掩码优化模块。BMPv2在COCO数据集上以1.5个平均精度（AP）点、在OCHuman数据集上以6个AP点超越了现有最佳方法，成为首个在OCHuman上超过50 AP的方法。我们证明了BMP对三维模型的二维提示能改善拥挤场景下的三维姿态估计，且二维姿态质量的提升直接有益于三维估计。在新OCHuman-Pose数据集上的结果表明，多人姿态性能受姿态预测精度的影响大于受检测精度的影响。代码、模型与数据可在 https://MiraPurkrabek.github.io/BBox-Mask-Pose/ 获取。