There are 44 repositories under openpose topic.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
pytorch implementation of openpose including Hand and Body Pose Estimation.
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署,支持Android与iOS。
Library for Fast and Flexible Human Pose Estimation
:basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.
Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)
online 3d openpose editor for stable diffusion and controlnet
3d openpose editor for stable diffusion and controlnet
OpenPose's Unity Plugin for Unity users
This repository contains a pure C++ ONNX implementation of multiple offline AI models, such as StableDiffusion (1.5 and XL), ControlNet, Midas, HED and OpenPose.
Everybody dance now reproduced in pytorch
Training repository for OpenPose
Markerless kinematics with any cameras — From 2D Pose estimation to 3D OpenSim motion
Perform Human Pose Estimation in OpenCV Using OpenPose MobileNet
Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,
Python bindings for the Openpose library
Implement of Openpose use Tensorflow
CT-Net, OpenPose, LIP_JPPNet, DensePose running with ncnn⚡服装迁移/虚拟试穿⚡ClothingTransfer/Virtual-Try-On⚡
tf-openpose Based iOS Project
A collection of ControlNet poses
A tensorflow implementation of Arxiv Paper "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose "(https://arxiv.org/abs/1811.12004)
This is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !
Behavioral segmentation of open field in DeepLabCut, or B-SOID ("B-side"), is a pipeline that pairs unsupervised pattern recognition with supervised classification to achieve fast predictions of behaviors that are not predefined by users.
Openpose implementation using darknet
Detects the sitting position of a person
Compute 2D human pose and angles from a video or a webcam.
The baseline project for inferencing various Pose Estimation tflite models with TFLiteSwift on iOS
ROS wrapper for OpenPose
Code for estimating social distances from RGB cameras.
:basketball: Judging basketball shots and analyzing shooting pose with machine learning
Posture recognition based on common camera
Real-time 3D multi-person detection made easy with OpenPose and the ZED