OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

OpenMMLab Pose Estimation Toolbox and Benchmark.

Real-time pose estimation accelerated with NVIDIA TensorRT

Mask R-CNN for Human Pose Estimation on Keras and TensorFlow.

Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.

Code repository for the paper: Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild (ICCV 2021)

Forecasting Characteristic 3D Poses of Human Actions (CVPR'22) 🏃‍♂️

Implement Human Pose Transfer papers with Pytorch

[ECCV 2022] SAGA: Stochastic Whole-Body Grasping with Contact

[CVPR 2023] DiffPose: Toward More Reliable 3D Pose Estimation

An unofficial implementation of ViTPose [Y. Xu et al., 2022]

Visualize 3d humans' skeletons(body+hands) in ros rviz. The 2d joints are detected by openpose; The depth is from depth image.

Code for "Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation"

Train a stacked hourglass deep neural network for human pose estimation on the COCO 2017 dataset.

The testing code for OriNet

Reposing Humans by Warping 3D Features

Easy and fast 2d human pose estimation using SOTA ViTPose [Y. Xu et al., 2022] finetuned on 25 keypoints skeleton (COCO + Feet)

Python wrapper library for Intel distribution of OpenVINO and Open Model Zoo (OMZ) models. User can use DL by simple function calls with this library.

A simple wrapper to localize human joints from images/video frames for multiple subjects.

Monitor Your Workout through a Webcam/IP Camera. No equipment is required, other than a camera and a laptop. This application could potentially replace a personal trainer, making it the idea app for workout.