PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
This work addresses the problem of slow inference speeds in multi-person pose estimation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the inefficiency of separate localization and association in multi-person pose estimation by introducing PoseDet, a framework that performs both simultaneously, achieving unprecedented speed and competitive accuracy on the COCO benchmark.
Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additional computation and a waste of time. This paper, however, presents a novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed. Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. The proposed pose embedding contains semantic and geometric information, allowing us to access discriminative and informative features efficiently. It is utilized for candidate classification and body joint localization in PoseDet, leading to robust predictions of various poses. This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods. Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available.