Browse SoTA > Computer Vision > 3D Human Pose Estimation > 3D Absolute Human Pose Estimation

3D Absolute Human Pose Estimation

4 papers with code · Computer Vision

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 )

Benchmarks

Greatest papers with code

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

CVPR 2017 Microsoft/USBuildingFootprints

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.

3D ABSOLUTE HUMAN POSE ESTIMATION SEMANTIC SEGMENTATION

Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach

CVPR 2020 CHUNYUWANG/imu-human-pose-pytorch

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.

3D ABSOLUTE HUMAN POSE ESTIMATION