MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model

TL;DR

MDPose introduces a single-stage, real-time multi-person pose estimation framework that models keypoint distributions with a mixture density approach, improving accuracy in occlusion scenarios and inference speed.

Contribution

The paper proposes MDPose, a novel mixture density model for single-stage, instance-aware pose estimation that simplifies the pipeline and enhances occlusion handling.

Findings

Achieves state-of-the-art performance on occlusion-heavy datasets

Significantly improves inference speed over previous methods

Successfully models high-dimensional joint distributions of keypoints

Abstract

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.