human-pose-estimation

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

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Sandbox for training deep learning networks

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

⚡️The spatial perception framework for rapidly building smart robots and spaces

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

Visual Imitation Enables Contextual Humanoid Control. CoRL 2025, Best Student Paper Award.

[CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"

Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.

Estimate absolute 3D human poses from RGB images.

Distribution-Aware Coordinate Representation for Human Pose Estimation

[ICLR 2026] An unified model for 4D human-scene reconstruction

"Learning Delicate Local Representations for Multi-Person Pose Estimation" (ECCV 2020 Spotlight) & (COCO 2019 Human Keypoint Detection Challenge Winner) & (COCO 2019 Best Paper Award)