Hands Deep in Deep Learning for Hand Pose Estimation

February 24, 2015 · Entered Twilight · 🏛 arXiv.org

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, data, src

Authors Markus Oberweger, Paul Wohlhart, Vincent Lepetit arXiv ID 1502.06807 Category cs.CV: Computer Vision Citations 380 Venue arXiv.org Repository https://github.com/moberweger/deep-prior ⭐ 62 Last Checked 1 month ago

Abstract

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.