OpenposeOpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Stars: ✭ 22,892 (+16609.49%)
FastPosepytorch realtime multi person keypoint estimation
Stars: ✭ 36 (-73.72%)
Lightweight Human Pose Estimation.pytorchFast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
Stars: ✭ 958 (+599.27%)
kapaoKAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
Stars: ✭ 604 (+340.88%)
ICONICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (+367.88%)
Pytorch Human Pose EstimationImplementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
Stars: ✭ 346 (+152.55%)
HopeSource code of CVPR 2020 paper, "HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation"
Stars: ✭ 184 (+34.31%)
Monoloco[ICCV 2019] Official implementation of "MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation" in PyTorch + Social Distancing
Stars: ✭ 242 (+76.64%)
MobilePoseLight-weight Single Person Pose Estimator
Stars: ✭ 588 (+329.2%)
Multiposenet.pytorchpytorch implementation of MultiPoseNet (ECCV 2018, Muhammed Kocabas et al.)
Stars: ✭ 191 (+39.42%)
A2jCode for paper "A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image". ICCV2019
Stars: ✭ 190 (+38.69%)
Keypoint Communities[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".
Stars: ✭ 255 (+86.13%)
Trt poseReal-time pose estimation accelerated with NVIDIA TensorRT
Stars: ✭ 525 (+283.21%)
Deepstream pose estimationThis is a sample DeepStream application to demonstrate a human pose estimation pipeline.
Stars: ✭ 168 (+22.63%)
MocapnetWe present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
Stars: ✭ 194 (+41.61%)
rmpe dataset serverRealtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.
Stars: ✭ 14 (-89.78%)
openpifpafOfficial implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Stars: ✭ 900 (+556.93%)
Pose Residual Network PytorchCode for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067
Stars: ✭ 277 (+102.19%)
PoseflowPoseFlow: Efficient Online Pose Tracking (BMVC'18)
Stars: ✭ 330 (+140.88%)
Tf Pose EstimationDeep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+2714.6%)
AlphaposeReal-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Stars: ✭ 5,697 (+4058.39%)
OpenpifpafOfficial implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Stars: ✭ 662 (+383.21%)
Lightweight SegmentationLightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).
Stars: ✭ 261 (+90.51%)
jeelizGlanceTrackerJavaScript/WebGL lib: detect if the user is looking at the screen or not from the webcam video feed. Lightweight and robust to all lighting conditions. Great for play/pause videos if the user is looking or not, or for person detection. Link to live demo.
Stars: ✭ 68 (-50.36%)
Pytorch PoseA PyTorch toolkit for 2D Human Pose Estimation.
Stars: ✭ 932 (+580.29%)
PazHierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.
Stars: ✭ 131 (-4.38%)
MetrabsThis is a computer vision algorithm that takes a single RGB image as the input and estimates 3D human poses as the output.
Stars: ✭ 123 (-10.22%)
SzlA lightweight, embeddable scripting language
Stars: ✭ 134 (-2.19%)
BuildArmbian Linux build framework
Stars: ✭ 1,827 (+1233.58%)
NanoLightweight, facility, high performance golang based game server framework
Stars: ✭ 1,888 (+1278.1%)
Ov2slamOV²SLAM is a Fully Online and Versatile Visual SLAM for Real-Time Applications
Stars: ✭ 119 (-13.14%)
VerseNetwork protocol for real-time sharing between graphical applications
Stars: ✭ 121 (-11.68%)
SignalsGeneral purpose modern C++ Signal-Slot providing ease of use, flexibility and extremely high performance aiming to replace traditional interfaces in real-time applications
Stars: ✭ 137 (+0%)
Ws MonitoringA simple & lightweight realtime monitoring web UI + server in Node.js
Stars: ✭ 130 (-5.11%)
O22D Game Engine with visual WYSIWYG editor
Stars: ✭ 121 (-11.68%)
Uc Os2µC/OS-II is a preemptive, highly portable, and scalable real-time kernels. Designed for ease of use on a huge number of CPU architectures.
Stars: ✭ 120 (-12.41%)
EasyloggerAn ultra-lightweight(ROM<1.6K, RAM<0.3k), high-performance C/C++ log library. | 一款超轻量级(ROM<1.6K, RAM<0.3k)、高性能的 C/C++ 日志库
Stars: ✭ 1,968 (+1336.5%)
CrepeThe thin API stack.
Stars: ✭ 120 (-12.41%)
React Select MeFast 🐆. Lightweight 🐜. Configurable 🐙. Easy to use 🦄. Give it a shot 👉🏼
Stars: ✭ 119 (-13.14%)
Electron GlobalOne Electron instance for multiple apps
Stars: ✭ 129 (-5.84%)
Deep sort yolov3Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow
Stars: ✭ 1,590 (+1060.58%)