HPERL: 3D Human Pose Estimation from RGB and LiDAR
This addresses the need for more accurate human pose estimation for applications like autonomous driving, though it is incremental by extending existing methods with LiDAR.
The paper tackles the problem of inaccurate absolute 3D human pose estimation in-the-wild by proposing an end-to-end architecture that uses RGB and LiDAR data, achieving unprecedented precision.
In-the-wild human pose estimation has a huge potential for various fields, ranging from animation and action recognition to intention recognition and prediction for autonomous driving. The current state-of-the-art is focused only on RGB and RGB-D approaches for predicting the 3D human pose. However, not using precise LiDAR depth information limits the performance and leads to very inaccurate absolute pose estimation. With LiDAR sensors becoming more affordable and common on robots and autonomous vehicle setups, we propose an end-to-end architecture using RGB and LiDAR to predict the absolute 3D human pose with unprecedented precision. Additionally, we introduce a weakly-supervised approach to generate 3D predictions using 2D pose annotations from PedX [1]. This allows for many new opportunities in the field of 3D human pose estimation.