Dual Path Networks for Multi-Person Human Pose Estimation
This work addresses pose estimation in natural scenes, offering incremental improvements in efficiency and accuracy for computer vision applications.
The authors tackled multi-person human pose estimation by designing a dual-path network to improve regression of keypoints and limb association vectors, achieving smaller, faster, and more accurate results compared to OpenPose.
The task of multi-person human pose estimation in natural scenes is quite challenging. Existing methods include both top-down and bottom-up approaches. The main advantage of bottom-up methods is its excellent tradeoff between estimation accuracy and computational cost. We follow this path and aim to design smaller, faster, and more accurate neural networks for the regression of keypoints and limb association vectors. These two regression tasks are naturally dependent on each other. In this work, we propose a dual-path network specially designed for multi-person human pose estimation, and compare our performance with the openpose network in aspects of model size, forward speed, and estimation accuracy.