3D Multi-Person Pose Estimation
32 papers with code • 5 benchmarks • 4 datasets
This task aims to solve root-relative 3D multi-person pose estimation. No human bounding box and root joint coordinate groundtruth are used in testing time.
( Image credit: RootNet )
Benchmarks
These leaderboards are used to track progress in 3D Multi-Person Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Multi-Person Pose Estimation models and implementations
Panoptic
MuPoTS-3D
AGORA
Store dataset
Subtasks
Most implemented papers
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.
Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
zju3dv/EasyMocap
•
•
CVPR 2019
This paper addresses the problem of 3D pose estimation for multiple people in a few calibrated camera views.
XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
rwightman/pytorch-image-models
•
•
The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy.
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
mks0601/3DMPPE_POSENET_RELEASE
•
•
ICCV 2019
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
To further verify the scalability of our method, we propose a new large-scale multi-human dataset with 12 to 28 camera views.
VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
microsoft/voxelpose-pytorch
•
•
ECCV 2020
In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we present an end-to-end solution which directly operates in the $3$D space, therefore avoids making incorrect decisions in the 2D space.
Monocular, One-stage, Regression of Multiple 3D People
Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
Direct Multi-view Multi-person 3D Pose Estimation
Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks.
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop
nkolot/SPIN
•
•
ICCV 2019
Our approach is self-improving by nature, since better network estimates can lead the optimization to better solutions, while more accurate optimization fits provide better supervision for the network.
4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras
Our method enables a realtime online motion capture system running at 30fps using 5 cameras on a 5-person scene.
