Open Pose is a Large Vision Model (LVM) designed for real-time multi-person human pose detection in images and videos. It excels in robustly detecting and localizing human body, hand, face, and foot keypoints—up to 135 per person—without requiring special suits or markers, making it valuable for computer vision tasks involving human pose understanding. Some other noteworthy use cases of Open Pose include sports analytics, healthcare monitoring, and gesture recognition, where precise and real-time human motion analysis is essential. | Metric | Value | |--------------------|--------------------| | Parameter Count | Unknown | | Mixture of Experts | No | | Context Length | Unknown | | Multilingual | No | | Quantized* | Yes | | Precision* | FP8 | *_Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers._