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

August 28, 2017 · Entered Twilight · 🏛 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

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

Authors Markus Oberweger, Vincent Lepetit arXiv ID 1708.08325 Category cs.CV: Computer Vision Citations 251 Venue 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) Repository https://github.com/moberweger/deep-prior-pp ⭐ 146 Last Checked 1 month ago

Abstract

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 https://github.com/moberweger/deep-prior-pp .