82 Open source projects that are alternatives of or similar to Expose

A collection of awesome resources in Human Pose estimation.

This repository implements a demo of the Human pose estimation via Convolutional Part Heatmap Regression paper.

Human 3.6M 3D human pose dataset fetcher

Real-time 3D human pose estimation, implemented by tensorflow

Code for our ICCV 19 paper : Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3

Official implementation of ACCV 2020 paper "3D Human Motion Estimation via Motion Compression and Refinement" (Identical repo to https://github.com/KlabCMU/MEVA, will be kept in sync)

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

Pytorch version of Realtime Multi-Person Pose Estimation project

Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)

Real-time pose estimation accelerated with NVIDIA TensorRT

Posture recognition based on common camera

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data"

Multi-person Human Pose Estimation with HigherHRNet in Pytorch

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

This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.

This is a computer vision algorithm that takes a single RGB image as the input and estimates 3D human poses as the output.

🌌 OpenVTuber-虚拟アイドル共享计划 An application of real-time face and gaze analyzation via deep nerual networks.

Code for "Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation" (CVPR 2018)

Code for "Quantized Densely Connected U-Nets for Efficient Landmark Localization" (ECCV 2018) and "CU-Net: Coupled U-Nets" (BMVC 2018 oral)

Human Pose Estimation Related Publication

This is the proposal network for MultiPerson Pose Estimation.

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

pytorch implementation of MultiPoseNet (ECCV 2018, Muhammed Kocabas et al.)

This is a sample DeepStream application to demonstrate a human pose estimation pipeline.

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

OpenPose wrapper written in C++ and C# for Windows

🏃‍♀️ A curated list about human motion capture, analysis and synthesis.

Code for ICCV2021 paper PARE: Part Attention Regressor for 3D Human Body Estimation

PyTorch implementation of V2V-PoseNet with IntegralPose/PoseFix loss

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

PyTorch Implementation of Realtime Multi-Person Pose Estimation project.

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

Repository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)

BlazePoseBarracuda is a human 2D/3D pose estimation neural network that runs the Mediapipe Pose (BlazePose) pipeline on the Unity Barracuda with GPU.

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

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation

2D&3D human pose estimation

[ICCV 2019] Official implementation of "MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation" in PyTorch + Social Distancing

implementation of PersonLab(https://arxiv.org/abs/1803.08225) using TF-slim

Realtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.

Fast and accurate Human Pose Estimation using ShelfNet with PyTorch

Code for "Learning Feature Pyramids for Human Pose Estimation" (ICCV 2017)

Human3.6M downloader by Python

[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".

A PyTorch toolkit for 2D Human Pose Estimation.

This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.

💃 Real-time single person pose estimation for Android and iOS.

Using DenseNet for human pose estimation based on TensorFlow.

Keras version of Realtime Multi-Person Pose Estimation project

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

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

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.

A PyTorch port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

Bilevel Online Adaptation for Human Mesh Reconstruction

We developed a method animating a statistical 3D human model for biomechanical analysis to increase accessibility for non-experts, like patients, athletes, or designers.

ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)

pytorch realtime multi person keypoint estimation

Sandbox for training deep learning networks