Hands Deep in Deep Learning for Hand Pose Estimation

02/24/2015
by   Markus Oberweger, et al.
0

We introduce and evaluate several architectures for Convolutional Neural Networks to predict the 3D joint locations of a hand given a depth map. We first show that a prior on the 3D pose can be easily introduced and significantly improves the accuracy and reliability of the predictions. We also show how to use context efficiently to deal with ambiguities between fingers. These two contributions allow us to significantly outperform the state-of-the-art on several challenging benchmarks, both in terms of accuracy and computation times.

READ FULL TEXT
research
07/15/2019

FastV2C-HandNet: Fast Voxel to Coordinate Hand Pose Estimation with 3D Convolutional Neural Networks

Hand pose estimation from monocular depth images has been an important a...
research
10/06/2018

Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images

As a fundamental and challenging problem in computer vision, hand pose e...
research
05/21/2021

Embracing New Techniques in Deep Learning for Estimating Image Memorability

Various work has suggested that the memorability of an image is consiste...
research
04/02/2018

Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints

Accurate 3D hand pose estimation plays an important role in Human Machin...
research
08/28/2017

DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation

DeepPrior is a simple approach based on Deep Learning that predicts the ...
research
11/11/2021

Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation

While hand pose estimation is a critical component of most interactive e...
research
09/30/2016

Training a Feedback Loop for Hand Pose Estimation

We propose an entirely data-driven approach to estimating the 3D pose of...

Please sign up or login with your details

Forgot password? Click here to reset