ER-Net: Efficient Recalibration Network for Multi-view Multi-person 3D Pose Estimation

Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application scenarios. With the introduction of end-to-end direct regression methods, the field has reached a new stage of development. However, the regression results are still not accurate enough even for the optimal method for the joints that are more heavily influenced by external factors. In this paper, we propose an effective feature recalibration module based on the channel attention mechanism and an optimal calibration strategy, which is applied to a multi-view multi-person 3D human pose estimation task backbone network to achieve improved detection accuracy for joints that are more severely affected by external factors. Specifically, we achieve optimal weight adjustment of joint feature information through a recalibration module based on a channel attention mechanism and an optimal calibration strategy, which enables the model to learn the dependencies between joints and the dependencies between people and their corresponding joints. We call this method the Efficient Recalibration Network (ER-Net). Finally, experiments were conducted on two benchmark datasets for this task, Campus, and Shelf, PCP reached 97.3 percent and 98.3 percent, respectively.