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

Sandbox for training deep learning networks

The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

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

[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals

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

A PyTorch toolkit for 2D Human Pose Estimation.

Real-time pose estimation accelerated with NVIDIA TensorRT

This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

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

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

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

ExPose - EXpressive POse and Shape rEgression

pytorch version of "End-to-end Recovery of Human Shape and Pose"

Training repository for OpenPose

Multi-person Human Pose Estimation with HRNet in Pytorch