MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
This addresses the problem of real-time, accurate pose estimation for computer vision applications, representing a strong incremental advance with significant speed gains.
The paper tackles multi-person pose estimation by introducing MultiPoseNet, which uses a Pose Residual Network for assignment, achieving a 4-point mAP improvement over previous bottom-up methods and running at 23 frames/sec on the COCO dataset.
In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and pose estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate poses by assigning keypoints to person instances. On the COCO keypoints dataset, our pose estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: https://github.com/mkocabas/pose-residual-network