Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

Saurabh Sharma, Pavan Teja Varigonda, Prashast Bindal, Abhishek Sharma, Arjun Jain; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 2325-2334

Abstract


Monocular 3D human-pose estimation from static images is a challenging problem, due to the curse of dimensionality and the ill-posed nature of lifting 2D-to-3D. In this paper, we propose a Deep Conditional Variational Autoencoder based model that synthesizes diverse anatomically plausible 3D-pose samples conditioned on the estimated 2D-pose. We show that CVAE-based 3D-pose sample set is consistent with the 2D-pose and helps tackling the inherent ambiguity in 2D-to-3D lifting. We propose two strategies for obtaining the final 3D pose- (a) depth-ordering/ordinal relations to score and weight-average the candidate 3D-poses, referred to as OrdinalScore, and (b) with supervision from an Oracle. We report close to state-of-the-art results on two benchmark datasets using OrdinalScore, and state-of-the-art results using the Oracle. We also show that our pipeline yields competitive results without paired image-to-3D annotations. The training and evaluation code is available at https://github.com/ssfootball04/generative_pose.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Sharma_2019_ICCV,
author = {Sharma, Saurabh and Varigonda, Pavan Teja and Bindal, Prashast and Sharma, Abhishek and Jain, Arjun},
title = {Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}