Learning to Estimate 3D Hand Pose from Single RGB Images (2017-05-03T00:00:00.000000Z)

TL;DR

A deep network is proposed that learns a network-implicit 3D articulation prior that yields good estimates of the 3D pose from regular RGB images, and a large scale 3D hand pose dataset based on synthetic hand models is introduced.

Abstract

Low-cost consumer depth cameras and deep learning have enabled reasonable 3D hand pose estimation from single depth images. In this paper, we present an approach that estimates 3D hand pose from regular RGB images. This task has far more ambiguities due to the missing depth information. To this end, we propose a deep network that learns a network-implicit 3D articulation prior. Together with detected keypoints in the images, this network yields good estimates of the 3D pose. We introduce a large scale 3D hand pose dataset based on synthetic hand models for training the involved networks. Experiments on a variety of test sets, including one on sign language recognition, demonstrate the feasibility of 3D hand pose estimation on single color images.

Authors

T. Brox

22 papers

Christiane Zimmermann

2 papers

TL;DR

Abstract

Authors

References29 items

Deep Multitask Architecture for Integrated 2D and 3D Human Sensing

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

3D Human Pose Estimation = 2D Pose Estimation + Matching

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

Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision

3D Human Pose Estimation from a Single Image via Distance Matrix Regression

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

3D Human pose estimation: A review of the literature and analysis of covariates

3D Hand Pose Tracking and Estimation Using Stereo Matching

Real-Time Joint Tracking of a Hand Manipulating an Object from RGB-D Input

A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image

Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image

Model-Based Deep Hand Pose Estimation

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Convolutional Pose Machines

Training a Feedback Loop for Hand Pose Estimation

Accurate, Robust, and Flexible Real-time Hand Tracking

Hands Deep in Deep Learning for Hand Pose Estimation

Adam: A Method for Stochastic Optimization

Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks

Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

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

DeepPose: Human Pose Estimation via Deep Neural Networks

Et al

Estimating 3D hand pose from a cluttered image

German Fingerspelling database

Efficient model-based 3D tracking of hand articulations using Kinect

Modeling Image Variability in Appearance-Based Gesture Recognition

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names