Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
This addresses the ill-posed challenge of 2D-to-3D lifting in computer vision for applications like robotics and AR, with incremental improvements in accuracy.
The paper tackles the problem of monocular 3D human pose estimation from static images by proposing a deep conditional variational autoencoder model that generates diverse 3D pose samples conditioned on 2D poses, using ordinal ranking to select the final pose, achieving close to state-of-the-art results on benchmarks.
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.