431 Open source projects that are alternatives of or similar to Pytorch Human Pose Estimation

Real-time pose estimation accelerated with NVIDIA TensorRT

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

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

A collection of awesome resources in Human Pose estimation.

A PyTorch toolkit for 2D Human Pose Estimation.

Posture recognition based on common camera

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

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

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

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

pytorch realtime multi person keypoint estimation

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

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

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

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

Sandbox for training deep learning networks

Keras version of Realtime Multi-Person Pose Estimation project

OpenMMLab Pose Estimation Toolbox and Benchmark.

Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.

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

Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067

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

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.

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

IceData: Datasets Hub for the *IceVision* Framework

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Pytorch Code for CVPR2019 paper "Fast Human Pose Estimation" https://arxiv.org/abs/1811.05419

ECCV2020 - Official code repository for the paper : STAR - A Sparse Trained Articulated Human Body Regressor

PyTorch-style and human-readable RegNet with a spectrum of pre-trained models

Spleeter is Deezer source separation library with pretrained models written in Python and uses Tensorflow. It makes it easy to train source separation model (assuming you have a dataset of isolated sources), and provides already trained state of the art model for performing various flavour of separation :

Official PyTorch Implementation of "Ego-Pose Estimation and Forecasting as Real-Time PD Control". ICCV 2019.

separate from 6dpose repo for deployment

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

Bilevel Online Adaptation for Human Mesh Reconstruction

[cvpr 20] Demo, training and evaluation code for joint hand-object pose estimation in sparsely annotated videos

PoseFlow: Efficient Online Pose Tracking (BMVC'18)

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

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

Source Code for "DeepURL: Deep Pose Estimation Framework for Underwater Relative Localization", submitted to IROS 2020

Detect various irregularities of a product as it moves along a conveyor belt.

Multi-Stage Pose Network

HyperFace

An extension of Open3D to address 3D Machine Learning tasks

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

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Neural syntax annotator, supporting sequence labeling, lemmatization, and dependency parsing.

InceptionV3, InceptionV4, Inception-Resnet pretrained models for Torch7 and PyTorch

Python scripts for performing 3D human pose estimation using the Mobile Human Pose model in ONNX.

PyTorch implementation of "Pyramid Scene Parsing Network".

Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018)' paper

[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations

Official TensorFlow implementation of "PoseFix: Model-agnostic General Human Pose Refinement Network", CVPR 2019

Full pipeline for TianChi FashionAI clothes keypoints detection compitetion in TensorFlow

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

TensorRT Examples (TensorRT, Jetson Nano, Python, C++)

A curated list of action recognition and related area resources

Finetuning any DNN for better embedding on neural search tasks

The official repo for CVPR2021——ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search.

Mask RCNN in TensorFlow