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

by   Markus Oberweger, et al.

DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map. Since its publication early 2015, it has been outperformed by several impressive works. Here we show that with simple improvements: adding ResNet layers, data augmentation, and better initial hand localization, we achieve better or similar performance than more sophisticated recent methods on the three main benchmarks (NYU, ICVL, MSRA) while keeping the simplicity of the original method. Our new implementation is available at .



page 1

page 2

page 3

page 4


HandAugment: A Simple Data Augmentation for HANDS19 Challenge Task 1 – Depth-Based 3D Hand Pose Estimation

Hand pose estimation from 3D depth images, has been explored widely usin...

Automating Augmentation Through Random Unidimensional Search

It is no secret amongst deep learning researchers that finding the right...

Active Learning for Bayesian 3D Hand Pose Estimation

We propose a Bayesian approximation to a deep learning architecture for ...

Hands Deep in Deep Learning for Hand Pose Estimation

We introduce and evaluate several architectures for Convolutional Neural...

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...

Dense 3D Regression for Hand Pose Estimation

We present a simple and effective method for 3D hand pose estimation fro...

Bi-stream Pose Guided Region Ensemble Network for Fingertip Localization from Stereo Images

In human-computer interaction, it is important to accurately estimate th...
This week in AI

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