OpenPose
Real-time multi-person pose estimation by CMU for body, hand, and face keypoints.
About
OpenPose from Carnegie Mellon University was the first real-time system to jointly detect body, foot, hand, and facial keypoints, up to 135 points, on single images. It runs on CUDA GPUs and is widely used in research and creative pose-driven applications, and it draws on the CMU Panoptic Studio dataset. It is distributed under a custom license that restricts commercial use.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Custom
- Minimum VRAM
- 6 GB
- Added
- Apr 3, 2026
Related Tools
Simple and effective multi-object tracking using every detection box.
Monocular depth estimation model producing detailed depth maps from single images.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Self-supervised vision transformer by Meta producing universal visual features.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Robust multi-object tracking combining motion and appearance cues.