3D Human Pose Estimation is the task of estimating the pose of a human from a picture or set of video frames.
( Image credit: 3d-pose-baseline )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Dynamics of human body skeletons convey significant information for human action recognition.
#2 best model for Action Recognition In Videos on IRD
We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints.
#18 best model for 3D Human Pose Estimation on Human3.6M
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.
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.
#7 best model for 3D Human Pose Estimation on 3DPW (using extra training data)
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.
We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views.
SOTA for 3D Human Pose Estimation on Human3.6M (using extra training data)
We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild.
Deep learning for predicting or generating 3D human pose sequences is an active research area.