This task aims to solve absolute (not root-relative) 3D human pose estimation. This also means NO GROUNDTRUTH INFORMATION is used in testing stage including human bounding box and human root joint coordinate. Models are trained on subject 1,5,6,7,8 and tested on subject 9,11 without rigid alignment.
( Image credit: RootNet )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation.
Ranked #8 on Semantic Segmentation on NYU Depth v2
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
Ranked #1 on Root Joint Localization on Human3.6M
3D ABSOLUTE HUMAN POSE ESTIMATION 3D MULTI-PERSON POSE ESTIMATION (ABSOLUTE) 3D MULTI-PERSON POSE ESTIMATION (ROOT-RELATIVE) MONOCULAR 3D HUMAN POSE ESTIMATION MULTI-PERSON POSE ESTIMATION ROOT JOINT LOCALIZATION
Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research.
Ranked #1 on 3D Human Pose Estimation on 3D Poses in the Wild Challenge (MPJPE metric)
Then we lift the multi-view 2D poses to the 3D space by an Orientation Regularized Pictorial Structure Model (ORPSM) which jointly minimizes the projection error between the 3D and 2D poses, along with the discrepancy between the 3D pose and IMU orientations.
Ranked #1 on 3D Human Pose Estimation on Total Capture