3D Human Pose Estimation with Siamese Equivariant Embedding

09/19/2018
by   Márton Véges, et al.
0

In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/21/2019

Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates

3D human pose estimation is frequently seen as the task of estimating 3D...
research
03/03/2021

On the role of depth predictions for 3D human pose estimation

Following the successful application of deep convolutional neural networ...
research
09/13/2018

Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation

In this paper we present our winning entry at the 2018 ECCV PoseTrack Ch...
research
08/22/2023

PoseGraphNet++: Enriching 3D Human Pose with Orientation Estimation

Existing kinematic skeleton-based 3D human pose estimation methods only ...
research
05/09/2021

Estimation of 3D Human Pose Using Prior Knowledge

Estimating three-dimensional human poses from the positions of two-dimen...
research
12/01/2018

Accurate control of a pan-tilt system based on parameterization of rotational motion

A pan-tilt camera system has been adopted by a variety of fields since i...
research
09/10/2020

Orientation Keypoints for 6D Human Pose Estimation

Most realtime human pose estimation approaches are based on detecting jo...

Please sign up or login with your details

Forgot password? Click here to reset