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

09/13/2018
by   István Sárándi, et al.
0

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 among methods that use no additional pose datasets in training.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/20/2020

Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions

Occlusion degrades the performance of human pose estimation. In this pap...
research
09/19/2018

3D Human Pose Estimation with Siamese Equivariant Embedding

In monocular 3D human pose estimation a common setup is to first detect ...
research
06/04/2022

SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

We propose a method SPGNet for 3D human pose estimation that mixes multi...
research
07/12/2020

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

Heatmap representations have formed the basis of human pose estimation s...
research
06/15/2017

Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation

We propose a novel approach to 3D human pose estimation from a single de...
research
03/05/2020

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation

Heatmap representations have formed the basis of 2D human pose estimatio...
research
09/14/2020

Beyond Weak Perspective for Monocular 3D Human Pose Estimation

We consider the task of 3D joints location and orientation prediction fr...

Please sign up or login with your details

Forgot password? Click here to reset