Global Context for Convolutional Pose Machines
This work addresses pose estimation accuracy and speed for computer vision applications, representing an incremental improvement with a novel context module.
The paper tackles the problem of enhancing the empirical receptive field in Convolutional Pose Machines for articulated pose estimation by integrating a global context module, achieving state-of-the-art accuracy of 87.9% PCKh on the Look Into Person dataset and demonstrating faster performance than hourglass-based networks on the MPII benchmark.
Convolutional Pose Machine is a popular neural network architecture for articulated pose estimation. In this work we explore its empirical receptive field and realize, that it can be enhanced with integration of a global context. To do so U-shaped context module is proposed and compared with the pyramid pooling and atrous spatial pyramid pooling modules, which are often used in semantic segmentation domain. The proposed neural network achieves state-of-the-art accuracy with 87.9% PCKh for single-person pose estimation on the Look Into Person dataset. A smaller version of this network runs more than 160 frames per second while being just 2.9% less accurate. Generalization of the proposed approach is tested on the MPII benchmark and shown, that it faster than hourglass-based networks, while provides similar accuracy. The code is available at https://github.com/opencv/openvino_training_extensions/tree/develop/pytorch_toolkit/human_pose_estimation .