3D Human Pose Estimation is the task of estimating the pose of a human from a picture or set of video frames.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints.
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 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.
#5 best model for 3D Human Pose Estimation on Human3.6M
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.
#7 best model for 3D Human Pose Estimation on Human3.6M
We present the first method to capture the 3D total motion of a target person from a monocular view input.
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.
#2 best model for 3D Human Pose Estimation on Human3.6M
For the ECCV 2018 PoseTrack Challenge, we present a 3D human pose estimation system based mainly on the integral human pose regression method.
Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests.
Direct prediction of 3D body pose and shape remains a challenge even for highly parameterized deep learning models.
#4 best model for 3D Human Pose Estimation on Human3.6M