3D Human Pose Estimation

278 papers with code • 21 benchmarks • 43 datasets

3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.


Use these libraries to find 3D Human Pose Estimation models and implementations

Most implemented papers

Convolutional Pose Machines

CMU-Perceptual-Computing-Lab/convolutional-pose-machines-release CVPR 2016

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models.

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

yysijie/st-gcn 23 Jan 2018

Dynamics of human body skeletons convey significant information for human action recognition.

DensePose: Dense Human Pose Estimation In The Wild

facebookresearch/detectron2 CVPR 2018

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation.

A simple yet effective baseline for 3d human pose estimation

una-dinosauria/3d-pose-baseline ICCV 2017

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels.

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

DenisTome/Lifting-from-the-Deep-release CVPR 2017

We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.

End-to-end Recovery of Human Shape and Pose

open-mmlab/mmpose CVPR 2018

The main objective is to minimize the reprojection loss of keypoints, which allow our model to be trained using images in-the-wild that only have ground truth 2D annotations.

3D human pose estimation in video with temporal convolutions and semi-supervised training

facebookresearch/VideoPose3D CVPR 2019

We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints.

BlazePose: On-device Real-time Body Pose tracking

google/mediapipe 17 Jun 2020

We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices.

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

xingyizhou/pose-hg-3d ICCV 2017

We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

mks0601/V2V-PoseNet_RELEASE CVPR 2018

To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel likelihood for each keypoint.