Hand PointNet: 3D Hand Pose Estimation Using Point Sets

@inproceedings{Ge2018HandP3,
  title={Hand PointNet: 3D Hand Pose Estimation Using Point Sets},
  author={Liuhao Ge and Yujun Cai and Junwu Weng and Junsong Yuan},
  booktitle={CVPR},
  year={2018}
}
We present the detailed network architecture of the hand pose regression network in Figure 1, which is based on the architecture of hierarchical PointNet proposed in [7]. As can be seen, the hand pose regression network has three set abstraction levels. At the l-th level (l = 1, 2), Nl points are sampled using iterative farthest point sampling and k nearest neighboring points of each sampled point are grouped as a local region. Following [7], we search nearest points that are within a radius to… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 25 references

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

2017 IEEE International Conference on Computer Vision Workshops (ICCVW) • 2017
View 4 Excerpts
Highly Influenced

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 5 Excerpts
Highly Influenced

3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation from Single Depth Images

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 4 Excerpts

3D Object Classification via Spherical Projections

2017 International Conference on 3D Vision (3DV) • 2017

Similar Papers

Loading similar papers…