OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation - CMU-Perceptual-Computing-Lab/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation - CMU-Perceptual-Computing-Lab/openpose

OpenPose可以实现人体动作、面部表情、手指运动等姿态估计，是卡耐基梅隆大学（CMU）基于卷积神经网络和监督学习并以caffe为框架开发的开源库。适用于单人和多人，具有极好的鲁棒性。是世界 …

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation - CMU-Perceptual-Computing-Lab/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation - CMU-Perceptual-Computing-Lab/openpose

The OpenPose documentation is available in 2 different formats, choose your preferred one! As a traditional website (recommended): cmu-perceptual-computing-lab.github.io/openpose.

OpenPose has represented the first real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images.

Mar 1, 2026 · 全新3D姿态编. Contribute to windFFYL/ComfyUI-3D-OpenPose-Editor2026 development by creating an account on GitHub.

Aug 3, 2024 · GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.

OpenPose has represented the first real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images.