HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization
This work addresses the challenge of accurately localizing absolute 3D positions of people in camera coordinates, which is crucial for applications like robotics and augmented reality, representing an incremental improvement over existing methods.
The paper tackles the problem of absolute root joint localization in multi-person 3D pose estimation by proposing HDNet, an end-to-end framework that estimates human depth in camera space, achieving state-of-the-art results on benchmark datasets like Human3.6M and MuPoTS-3D.
Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose. In this paper, we propose the Human Depth Estimation Network (HDNet), an end-to-end framework for absolute root joint localization in the camera coordinate space. Our HDNet first estimates the 2D human pose with heatmaps of the joints. These estimated heatmaps serve as attention masks for pooling features from image regions corresponding to the target person. A skeleton-based Graph Neural Network (GNN) is utilized to propagate features among joints. We formulate the target depth regression as a bin index estimation problem, which can be transformed with a soft-argmax operation from the classification output of our HDNet. We evaluate our HDNet on the root joint localization and root-relative 3D pose estimation tasks with two benchmark datasets, i.e., Human3.6M and MuPoTS-3D. The experimental results show that we outperform the previous state-of-the-art consistently under multiple evaluation metrics. Our source code is available at: https://github.com/jiahaoLjh/HumanDepth.