MDPose：基于混合密度模型的实时多人姿态估计
MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model
AI总结：
提出MDPose，一种基于混合密度模型的单阶段多人姿态估计框架，通过8层卷积头学习关键点联合分布，结合随机关键点分组策略，在OCHuman上达到最先进性能，并在MS COCO上显著提升推理速度。
摘要：
多人姿态估计的主要挑战之一在于实例感知的关键点估计。以往的方法通过利用现成的检测器、启发式的后分组过程或显式的实例识别过程来解决这一问题，这阻碍了推理速度的进一步提升，而推理速度对于实际应用而言是一个重要因素。从统计学的角度来看，这些用于识别实例的额外过程是必要的，以绕过学习人体关键点的高维联合分布，而这一分布是另一个主要挑战（即遮挡场景）的关键因素。在本工作中，我们提出了一种新颖的单阶段实例感知姿态估计框架，通过混合密度模型对人体关键点的联合分布进行建模，称为MDPose。我们的MDPose使用混合密度模型，并配备一个仅由8个卷积层组成的实例感知关键点头，来估计人体关键点坐标的分布。它通过最小化真实关键点的负对数似然来进行训练。此外，我们提出了一种简单而有效的训练策略，即随机关键点分组（RKG），该策略显著缓解了下溢问题，从而成功学习了关键点之间的关系。在包含高度遮挡人群图像的OCHuman数据集上，我们的MDPose通过成功学习人体关键点的高维联合分布，实现了最先进的性能。此外，得益于所提出的更为简单的单阶段流程，我们的MDPose在广泛使用的人体关键点数据集MS COCO上，在推理速度上表现出显著提升，同时保持了具有竞争力的准确性。
英文摘要：
One of the major challenges in multi-person pose estimation is instance-aware keypoint estimation. Previous methods address this problem by leveraging an off-the-shelf detector, heuristic post-grouping process or explicit instance identification process, hindering further improvements in the inference speed which is an important factor for practical applications. From the statistical point of view, those additional processes for identifying instances are necessary to bypass learning the high-dimensional joint distribution of human keypoints, which is a critical factor for another major challenge, the occlusion scenario. In this work, we propose a novel framework of single-stage instance-aware pose estimation by modeling the joint distribution of human keypoints with a mixture density model, termed as MDPose. Our MDPose estimates the distribution of human keypoints' coordinates using a mixture density model with an instance-aware keypoint head consisting simply of 8 convolutional layers. It is trained by minimizing the negative log-likelihood of the ground truth keypoints. Also, we propose a simple yet effective training strategy, Random Keypoint Grouping (RKG), which significantly alleviates the underflow problem leading to successful learning of relations between keypoints. On OCHuman dataset, which consists of images with highly occluded people, our MDPose achieves state-of-the-art performance by successfully learning the high-dimensional joint distribution of human keypoints. Furthermore, our MDPose shows significant improvement in inference speed with a competitive accuracy on MS COCO, a widely-used human keypoint dataset, thanks to the proposed much simpler single-stage pipeline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
