RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation

02/26/2019
by   Bastian Wandt, et al.
1

This paper addresses the problem of 3D human pose estimation from single images. While for a long time human skeletons were parameterized and fitted to the observation by satisfying a reprojection error, nowadays researchers directly use neural networks to infer the 3D pose from the observations. However, most of these approaches ignore the fact that a reprojection constraint has to be satisfied and are sensitive to overfitting. We tackle the overfitting problem by ignoring 2D to 3D correspondences. This efficiently avoids a simple memorization of the training data and allows for a weakly supervised training. One part of the proposed reprojection network (RepNet) learns a mapping from a distribution of 2D poses to a distribution of 3D poses using an adversarial training approach. Another part of the network estimates the camera. This allows for the definition of a network layer that performs the reprojection of the estimated 3D pose back to 2D which results in a reprojection loss function. Our experiments show that RepNet generalizes well to unknown data and outperforms state-of-the-art methods when applied to unseen data. Moreover, our implementation runs in real-time on a standard desktop PC.

READ FULL TEXT

page 6

page 8

research
05/17/2018

It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data

We address the problem of 3D human pose estimation from 2D input images ...
research
06/08/2021

A Synchronized Reprojection-based Model for 3D Human Pose Estimation

3D human pose estimation is still a challenging problem despite the larg...
research
06/04/2019

Semi- and Weakly-supervised Human Pose Estimation

For human pose estimation in still images, this paper proposes three sem...
research
09/13/2019

Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency

We present a novel data-driven regularizer for weakly-supervised learnin...
research
01/08/2023

CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations

To improve the generalization of 3D human pose estimators, many existing...
research
08/22/2018

Can 3D Pose be Learned from 2D Projections Alone?

3D pose estimation from a single image is a challenging task in computer...
research
10/17/2017

Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

In this paper, we propose a pose grammar to tackle the problem of 3D hum...

Please sign up or login with your details

Forgot password? Click here to reset