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

Matteo Ruggero Ronchi, Oisin Mac Aodha, Robert Eng, Pietro Perona

Research output: Contribution to conferencePaperpeer-review

Abstract / Description of output

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.
Original languageEnglish
Number of pages13
Publication statusPublished - 2 Sept 2018
Event29th British Machine Vision Conference (BMVC) - Northumbria University, Newcastle upon Tyne, United Kingdom
Duration: 3 Sept 20186 Sept 2018


Conference29th British Machine Vision Conference (BMVC)
Abbreviated titleBMVC 2018
Country/TerritoryUnited Kingdom
CityNewcastle upon Tyne
Internet address


Dive into the research topics of 'It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data'. Together they form a unique fingerprint.

Cite this