ML Anthology

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

Markus Oberweger, Vincent Lepetit
ICCVW 2017 pp. 585-594
doi:10.1109/ICCVW.2017.75 /iccvw/2017/oberweger2017iccvw-deepprior/

Abstract

DeepPrior [18] 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.

PDF ICCVW Semantic Scholar

Cite

Text

Oberweger and Lepetit. "DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.75

Markdown

[Oberweger and Lepetit. "DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/oberweger2017iccvw-deepprior/) doi:10.1109/ICCVW.2017.75

BibTeX

@inproceedings{oberweger2017iccvw-deepprior,
  title     = {{DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation}},
  author    = {Oberweger, Markus and Lepetit, Vincent},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {585-594},
  doi       = {10.1109/ICCVW.2017.75},
  url       = {https://mlanthology.org/iccvw/2017/oberweger2017iccvw-deepprior/}
}