HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision

@inproceedings{Wu2018HandMapRH,
  title={HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision},
  author={Xiaokun Wu and Daniel J. Finnegan and Eamonn O'Neill and Yongliang Yang},
  booktitle={ECCV},
  year={2018}
}
  • Xiaokun Wu, Daniel J. Finnegan, +1 author Yongliang Yang
  • Published in ECCV 2018
  • Computer Science
  • This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision. By leveraging the advantage of predicting heat maps of hand joints in detection-based methods, we propose to use dense feature maps through intermediate supervision in a regression-based framework that is not limited to the resolution of the heat map. Our dense feature maps are delicately designed to encode the hand geometry and the spatial relation between local joint and global hand. The… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 12 CITATIONS

    Silhouette-Net: 3D Hand Pose Estimation from Silhouettes

    VIEW 6 EXCERPTS
    CITES RESULTS & METHODS
    HIGHLY INFLUENCED

    Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data

    VIEW 1 EXCERPT
    CITES BACKGROUND

    3D Hand Shape and Pose From Images in the Wild

    Real-Time Hand Model Estimation from Depth Images for Wearable Augmented Reality Glasses

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES

    Stacked Hourglass Networks for Human Pose Estimation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

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

    VIEW 2 EXCERPTS

    BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis

    VIEW 1 EXCERPT

    Deep Multitask Architecture for Integrated 2D and 3D Human Sensing

    VIEW 1 EXCERPT

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

    VIEW 2 EXCERPTS

    First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations

    VIEW 1 EXCERPT