HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization (2020-07-17T00:00:00.000000Z)

TL;DR

The Human Depth Estimation Network (HDNet), an end-to-end framework for absolute root joint localization in the camera coordinate space, is proposed and shown to outperform the previous state-of-the-art consistently under multiple evaluation metrics.

Abstract

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: this https URL.

Authors

Gim Hee Lee

9 papers

Jiahao Lin

1 papers

TL;DR

Abstract

Authors

References31 items

Multi-Person 3D Human Pose Estimation from Monocular Images

Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image

Deep High-Resolution Representation Learning for Human Pose Estimation

Deep Ordinal Regression Network for Monocular Depth Estimation

Hand Pose Estimation via Latent 2.5D Heatmap Regression

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning

Single-Shot Multi-person 3D Pose Estimation from Monocular RGB

Integral Human Pose Regression

Cascaded Pyramid Network for Multi-person Pose Estimation

Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

A Coarse-Fine Network for Keypoint Localization

LCR-Net: Localization-Classification-Regression for Human Pose

A Simple Yet Effective Baseline for 3d Human Pose Estimation

Feature Pyramid Networks for Object Detection

RMPE: Regional Multi-person Pose Estimation

Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Stacked Hourglass Networks for Human Pose Estimation

Convolutional Pose Machines

Deep Residual Learning for Image Recognition

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

Microsoft COCO: Common Objects in Context

Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images

Mask R-CNN

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names