3D Human Pose Estimation
305 papers with code • 25 benchmarks • 46 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.
Benchmarks
These leaderboards are used to track progress in 3D Human Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Human Pose Estimation models and implementationsDatasets
Human3.6M
Waymo Open Dataset
3DPW
AMASS
MPI-INF-3DHP
DensePose
LSP
Panoptic
AGORA
TotalCapture
Subtasks
Most implemented papers
Convolutional Pose Machines
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
•
•
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.
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.
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.
BlazePose: On-device Real-time Body Pose tracking
google/mediapipe
•
•
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.
Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch
•
•
Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene.
