Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
This work addresses efficient multi-person pose estimation for computer vision applications, representing a strong specific gain rather than an incremental improvement.
The paper tackles the problem of detecting 2D poses of multiple people in images by introducing Part Affinity Fields (PAFs) to associate body parts with individuals, achieving realtime performance and winning the COCO 2016 keypoints challenge while surpassing previous state-of-the-art on the MPII benchmark.
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.