openpose and Realtime_Multi-Person_Pose_Estimation
These tools are competitors, as both implement real-time multi-person pose estimation, with "OpenPose" being a more extensive and widely adopted library that builds upon the foundational research described in the second project.
About openpose
CMU-Perceptual-Computing-Lab/openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Built on Part Affinity Fields (PAF) for efficient skeleton association, OpenPose uses a non-parametric representation that enables constant-time inference regardless of the number of people in frame—a key advantage over detection-based competitors. Supports multi-modal input (webcam, video, IP cameras, Flir hardware) and output formats (JSON, XML, PNG/AVI), with both C++ and Python APIs for custom preprocessing pipelines and integrations.
About Realtime_Multi-Person_Pose_Estimation
ZheC/Realtime_Multi-Person_Pose_Estimation
Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work