Edinburgh Research Explorer

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

Research output: Contribution to conferencePaper

Original languageEnglish
Pages1-13
Number of pages13
Publication statusPublished - 2 Sep 2018
Event29th British Machine Vision Conference (BMVC) - Northumbria University, Newcastle upon Tyne, United Kingdom
Duration: 3 Sep 20186 Sep 2018
http://www.bmvc2018.org/index.html

Conference

Conference29th British Machine Vision Conference (BMVC)
Abbreviated titleBMVC 2018
CountryUnited Kingdom
CityNewcastle upon Tyne
Period3/09/186/09/18
Internet address

Abstract

We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data. Despite showing considerable success for 2D pose estimation, the application of supervised machine learning to 3D pose estimation in real world images is currently hampered by the lack of varied training images with corresponding 3D poses. Most existing 3D pose estimation algorithms train on data that has either been collected in carefully controlled studio settings or has been generated synthetically. Instead, we take a different approach, and propose a 3D human pose estimation algorithm that only requires relative estimates of depth at training time. Such training signal, although noisy, can be easily collected from crowd annotators, and is of sufficient quality for enabling successful training and evaluation of 3D pose algorithms. Our results are competitive with fully supervised regression based approaches on the Human3.6M dataset, despite using significantly weaker training data. Our proposed algorithm opensthe door to using existing widespread 2D datasets for 3D pose estimation by allowing fine-tuning with noisy relative constraints, resulting in more accurate 3D poses.

Event

29th British Machine Vision Conference (BMVC)

3/09/186/09/18

Newcastle upon Tyne, United Kingdom

Event: Conference

ID: 122453448