Pose

Hourglass

Stacked Hourglass Networks for Human Pose Estimation (ECCV 2016)
residual module + pooling + upsampling (via interpolation)

OpenPose

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields (CVPR 2017)
CMU-Perceptual-Computing-Lab/openpose - commercial license required

HyperPose

re-implemented of OpenPose by tensorlayer. Version 2 of OpenPose Plus
tensorlayer/hyperpose: A Fast & Flexible Library for Human Pose Estimation - Apache 2.0 license

MSPN

Rethinking on Multi-Stage Networks for Human Pose Estimation (2019)

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multistage methods are seemingly more suited for the task, their performance in current practice is not as good as singlestage methods. This work studies this issue. We argue that the current multi-stage methods’ unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-tofine supervision.

pytorch