moberweger / deep-prior

Fast and accurate 3D hand pose estimation from single depth images
GNU General Public License v3.0
63 stars 23 forks source link

This work is superseded by DeepPrior++

DeepPrior - Accurate and Fast 3D Hand Pose Estimation

Author: Markus Oberweger oberweger@icg.tugraz.at

Requirements:

For a description of our method see:

M. Oberweger, P. Wohlhart, and V. Lepetit. Hands Deep in Deep Learning for Hand Pose Estimation. In Computer Vision Winter Workshop, 2015.

Setup:

Pretrained models:

Download pretrained models for ICVL and NYU dataset.

Datasets:

The ICVL dataset is trained for a time-of-flight camera, and the NYU dataset for a structured light camera. The annotations are different. See the papers for it.

D. Tang, H. J. Chang, A. Tejani, and T.-K. Kim. Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture. In Conference on Computer Vision and Pattern Recognition, 2014.

J. Tompson, M. Stein, Y. LeCun, and K. Perlin. Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks. ACM Transactions on Graphics, 33, 2014.