Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation

István Sárándi, Timm Linder, Kai Oliver Arras, Bastian Leibe
European Conference on Computer Vision (ECCV'18) - Workshops

In this paper we present our winning entry at the 2018 ECCV PoseTrack Challenge on 3D human pose estimation. Using a fully-convolutional backbone architecture, we obtain volumetric heatmaps per body joint, which we convert to coordinates using soft-argmax. Absolute person center depth is estimated by a 1D heatmap prediction head. The coordinates are back-projected to 3D camera space, where we minimize the L1 loss. Key to our good results is the training data augmentation with randomly placed occluders from the Pascal VOC dataset. In addition to reaching first place in the Challenge, our method also surpasses the state-of-the-art on the full Human3.6M benchmark when considering methods that use no extra pose datasets in training. Code for applying synthetic occlusions is availabe at https://github.com/isarandi/synthetic-occlusion.

» Show BibTeX

@inproceedings{Sarandi18ECCVW,
author = {I. S\'{a}r'{a}ndi and T. Linder and K. O. Arras and B. Leibe},
title = {Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation},
booktitle = {ECCV Workshops},
year = {2018}
}




Disclaimer Home Visual Computing institute RWTH Aachen University