Absolute Human Pose Estimation with Depth Prediction Network

11 Apr 2019  ·  Márton Véges, András Lőrincz ·

The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Multi-Person Pose Estimation (absolute) MuPoTS-3D Depth Prediction Network MPJPE 292 # 1
3D Multi-Person Pose Estimation (root-relative) MuPoTS-3D Depth Prediction Network MPJPE 120 # 2

Methods


No methods listed for this paper. Add relevant methods here