Trending repositories for topic 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.

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

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

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

This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).

IMU-based human skeletal pose estimation in C++11

[CVPR 2023] The official implementation of CVPR 2023 paper "Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes"

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

ExPose - EXpressive POse and Shape rEgression

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

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

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

This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).

IMU-based human skeletal pose estimation in C++11

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

[CVPR 2023] The official implementation of CVPR 2023 paper "Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes"

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

ExPose - EXpressive POse and Shape rEgression

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

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

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

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"

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

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

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

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

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.

ExPose - EXpressive POse and Shape rEgression

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

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

Sandbox for training deep learning networks

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

This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).

IMU-based human skeletal pose estimation in C++11

3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

[CVPR 2023] The official implementation of CVPR 2023 paper "Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes"

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

Official repository of Human3.6M 3D WholeBody (H3WB) dataset

Convert video to the bvh motion file

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).

IMU-based human skeletal pose estimation in C++11

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

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

CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.

3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

[CVPR 2023] The official implementation of CVPR 2023 paper "Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes"

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

Official repository of Human3.6M 3D WholeBody (H3WB) dataset

ExPose - EXpressive POse and Shape rEgression

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

Convert video to the bvh motion file

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

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

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

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

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

Real-time pose estimation accelerated with NVIDIA TensorRT

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

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

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

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

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

CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.

Sandbox for training deep learning networks

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

This is an official implementation of our CVPR 2021 paper "Deep Dual Consecutive Network for Human Pose Estimation" (https://openaccess.thecvf.com/content/CVPR2021/papers/Liu_Deep_Dual_Consecutive_Net...

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

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

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

A collection of awesome resources in Human Pose estimation.

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

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

Multi-person Human Pose Estimation with HRNet in Pytorch

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

Official code for "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation"

[ICCV, 2023] Multiple humans in 3D captured by dynamic and static cameras in 4K.

This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).

W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration

Official Code for ACM SIGGRAPH 2024 paper "Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging"

Repository for the SCA 2022 paper "Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-Grade VR Devices"

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

IMU-based human skeletal pose estimation in C++11

A simple and fast GUI tool to visualize and compare the SMPL sequences and scenes in real-time.

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

[3DV 2022] Pytorch implementation for 3D Event-based Human Pose Estimation

CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.

Official Code for ACM Transactions on Graphics (TOG) paper "SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data"

SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

This repo equips the official CLIFF [ECCV 2022 Oral] with better detector, better tracker. Support multi-person, motion interpolation, motion smooth and SMPLify fitting.

Python implementation accompanying the Transformer Inertial Poser paper at SIGGRAPH Asia 2022

Developing a virtual personal fitness tracker and exercise activity recognition A.I. using computer vision and deep learning.

This is an official implementation of our CVPR 2021 paper "Deep Dual Consecutive Network for Human Pose Estimation" (https://openaccess.thecvf.com/content/CVPR2021/papers/Liu_Deep_Dual_Consecutive_Net...

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[3DV 2024] POCO: 3D Pose and Shape Estimation using Confidence

Official Code for ACM SIGGRAPH 2024 paper "Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging"

W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration

Official code for "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation"

3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera [3DV'24]

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

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

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

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

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

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.

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

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

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

Estimate absolute 3D human poses from RGB images.

Sandbox for training deep learning networks

GUI for visualization and interactive editing of SMPL-family body models ie. SMPL, SMPL-X, MANO, FLAME.

Official repository of Human3.6M 3D WholeBody (H3WB) dataset

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

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

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

[3DV 2024] POCO: 3D Pose and Shape Estimation using Confidence

3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera [3DV'24]

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2

Probabilistic triangulation module applied to uncalibrated human pose estimation

Official Code for ACM Transactions on Graphics (TOG) paper "SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data"

YOLOv8-pose implementation using PyTorch

[WACV2024] Official PyTorch implimentation for ``Active Transfer Learning for Efficient Video-Specific Human Pose Estimation''

Efficient violence detection in surveillance videos using Human Skeletons and Motion Estimation

SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

visualization：filter、feature map、attention map、image-mask、grad-cam、human keypoint、guided-backpro

Developing a virtual personal fitness tracker and exercise activity recognition A.I. using computer vision and deep learning.

[ICCV, 2023] Multiple humans in 3D captured by dynamic and static cameras in 4K.

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

[ICCV 2023] Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

[CVPR 2023] DiffPose: Toward More Reliable 3D Pose Estimation

A simple and fast GUI tool to visualize and compare the SMPL sequences and scenes in real-time.

Code for our SIGGRAPH ASIA 2023 paper "Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture".

IMU-based human skeletal pose estimation in C++11