This page provides downloads for our BMVC'15 paper Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties.

(a)	(b)	(c)

A learned joint regressor might fail to recover the pose of a hand due to ambiguities or lack of training data (a). We make use of the inherent uncertainty of a regressor by enforcing it to generate multiple proposals (b). The crosses show the top three proposals for the proximal interphalangeal joint of the ring finger for which the corresponding ground truth position is drawn in green. The marker size of the proposals corresponds to degree of confidence. Our subsequent model-based optimisation procedure exploits these proposals to estimate the true pose (c).

Material

The BMVC'15 paper, extended abstract and slides can be downloaded here:

• Paper (PDF)

• Extended Abstract (PDF)

• Slides as PDF or PPTX

Citation

If you use this dataset or results, please cite our paper:

Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties
   Georg Poier, Konstantinos Roditakis, Samuel Schulter, Damien Michel, Horst Bischof and Antonis A. Argyros
   In Proc. British Machine Vision Conference (BMVC), 2015  

BibTeX reference for convenience:

@INPROCEEDINGS{poier15a,
  author = {Georg Poier and Konstantinos Roditakis and Samuel Schulter and Damien Michel and Horst Bischof and Antonis A. Argyros},
  title = {{Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties}},
  booktitle = {{Proc. British Machine Vision Conference (BMVC)}},
  year = {2015}
}