There are 68 repositories under pose-estimation topic.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Gluon CV Toolkit
Blendshape and kinematics calculator for Mediapipe/Tensorflow.js Face, Eyes, Pose, and Finger tracking models.
A curated list of action recognition and related area resources
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
A collection of awesome resources in Human Pose estimation.
OpenMMLab Pose Estimation Toolbox and Benchmark.
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Visual localization made easy with hloc
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
A procedural Blender pipeline for photorealistic training image generation
pytorch implementation of openpose including Hand and Body Pose Estimation.
Library for Fast and Flexible Human Pose Estimation
Human Pose estimation with TensorFlow framework
A PyTorch toolkit for 2D Human Pose Estimation.
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
:dancer: Real-time single person pose estimation for Android and iOS.
Keras version of Realtime Multi-Person Pose Estimation project
Network estimating 3D Handpose from single color images
:basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.
Monocular, One-stage, Regression of Multiple 3D People, ROMP[ICCV21], BEV[CVPR22]
LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
The collection of pre-trained, state-of-the-art AI models for ailia SDK
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Light-weight Single Person Pose Estimator
custom human activity recognition modules by pose estimation and cascaded inference using sklearn API
Real-time head pose estimation built with OpenCV and dlib
Perception toolkit for sim2real training and validation in Unity
NVIDIA Deep learning Dataset Synthesizer (NDDS)
KAPAO is a state-of-the-art single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
Estimate 3D face pose (6DoF) or 11 parameters of 3x4 projection matrix by a Convolutional Neural Network
Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.