Real-time multi-person pose estimation presents significant challenges in
balancing speed and precision. While two-stage top-down methods slow down as
the number of people in the image increases, existing one-stage methods often
fail to simultaneously deliver high accuracy and real-time performance. This
paper introduces RTMO, a one-stage pose estimation framework that seamlessly
integrates coordinate classification by representing keypoints using dual 1-D
heatmaps within the YOLO architecture, achieving accuracy comparable to
top-down methods while maintaining high speed. We propose a dynamic coordinate
classifier and a tailored loss function for heatmap learning, specifically
designed to address the incompatibilities between coordinate classification and
dense prediction models. RTMO outperforms state-of-the-art one-stage pose
estimators, achieving 1.1% higher AP on COCO while operating about 9 times
faster with the same backbone. Our largest model, RTMO-l, attains 74.8% AP on
COCO val2017 and 141 FPS on a single V100 GPU, demonstrating its efficiency and
accuracy. The code and models are available at
this https URL

RTMO 是一个一阶姿势估计框架，通过在 YOLO 架构中使用双 1-D 热图来表示关键点，实现了与自顶向下方法相当的准确性，同时保持了较高的速度。它采用了动态坐标分类器和定制的损失函数来解决坐标分类和密集预测模型之间的不兼容性。RTMO 在 COCO val2017 上达到了 74.8% 的平均精度（AP），在单个 V100 GPU 上实现了 141 FPS 的高效和准确性。