HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

by   Jiahao Lin, et al.

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.



There are no comments yet.



Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

Although significant improvement has been achieved in 3D human pose esti...

Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting

The 3D pose estimation from a single image is a challenging problem due ...

A Framework for Depth Estimation and Relative Localization of Ground Robots using Computer Vision

The 3D depth estimation and relative pose estimation problem within a de...

HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton

With increasing applications of 3D hand pose estimation in various human...

Estimating Parameters of the Tree Root in Heterogeneous Soil Environments via Mask-Guided Multi-Polarimetric Integration Neural Network

Ground-penetrating radar (GPR) has been used as a non-destructive tool f...

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Various deep learning techniques have been proposed to solve the single-...

Pose-based Modular Network for Human-Object Interaction Detection

Human-object interaction(HOI) detection is a critical task in scene unde...

Code Repositories


Code for "HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization"

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.