Training a Feedback Loop for Hand Pose Estimation

Markus Oberweger, Paul Wohlhart, Vincent Lepetit; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 3316-3324

Abstract

We propose an entirely data-driven approach to estimating the 3D pose of a hand given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop. The components of this feedback loop are also Deep Networks, optimized using training data. They remove the need for fitting a 3D model to the input data, which requires both a carefully designed fitting function and algorithm. We show that our approach outperforms state-of-the-art methods, and is efficient as our implementation runs at over 400 fps on a single GPU.

Related Material

[pdf]
[bibtex]
@InProceedings{Oberweger_2015_ICCV,
author = {Oberweger, Markus and Wohlhart, Paul and Lepetit, Vincent},
title = {Training a Feedback Loop for Hand Pose Estimation},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}