论文标题
人姿势估计的热图分布匹配
Heatmap Distribution Matching for Human Pose Estimation
论文作者
论文摘要
为了解决2D人姿势估计的任务，最近的大多数方法将此任务视为热图估计问题，并使用高斯平滑的热图作为优化目标来优化热图预测，并将使用像素损失（例如MSE）作为损失功能。在本文中，我们表明，以这种方式优化热图预测，在热图预测的优化过程中，人体关节定位的模型性能（这是该任务的内在目标）可能不会持续改进。为了解决这个问题，从新的角度来看，我们建议将热图预测的优化作为预测的热图和人体关节的点注释之间的分布匹配问题。通过这样做，我们提出的方法无需构建高斯平滑的热图，并且可以在优化热图预测期间实现更一致的模型性能。我们通过对可可数据集和MPII数据集进行了广泛的实验来展示我们提出的方法的有效性。
For tackling the task of 2D human pose estimation, the great majority of the recent methods regard this task as a heatmap estimation problem, and optimize the heatmap prediction using the Gaussian-smoothed heatmap as the optimization objective and using the pixel-wise loss (e.g. MSE) as the loss function. In this paper, we show that optimizing the heatmap prediction in such a way, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization process of the heatmap prediction. To address this problem, from a novel perspective, we propose to formulate the optimization of the heatmap prediction as a distribution matching problem between the predicted heatmap and the dot annotation of the body joint directly. By doing so, our proposed method does not need to construct the Gaussian-smoothed heatmap and can achieve a more consistent model performance improvement during the optimization of the heatmap prediction. We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the MPII dataset.
