Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation

@article{Liao2019Multiview2R,
  title={Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation},
  author={Haofu Liao and Wei-An Lin and Jiarui Zhang and Jingdan Zhang and Jiebo Luo and Shaohua Kevin Zhou},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={12630-12639}
}
  • Haofu Liao, Wei-An Lin, +3 authors Shaohua Kevin Zhou
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • We propose to tackle the problem of multiview 2D/3D rigid registration for intervention via a Point-Of-Interest Network for Tracking and Triangulation (POINT^2). POINT^2 learns to establish 2D point-to-point correspondences between the pre- and intra-intervention images by tracking a set of random POIs. The 3D pose of the pre-intervention volume is then estimated through a triangulation layer. In POINT^2, the unified framework of the POI tracker and the triangulation layer enables learning… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-5 OF 5 CITATIONS

    Multi-View Global 2D-3D Registration Based on Branch and Bound Algorithm

    VIEW 2 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Extremely Dense Point Correspondences using a Learned Feature Descriptor

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer-Assisted Interventions

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Appearance Learning for Image-based Motion Estimation in Tomography

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    Dynamic 2-D/3-D Rigid Registration Framework Using Point-To-Plane Correspondence Model

    Dilated FCN for Multi-Agent 2D/3D Medical Image Registration

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    A CNN Regression Approach for Real-Time 2D/3D Registration

    VIEW 2 EXCERPTS

    3D/2D model-to-image registration by imitation learning for cardiac procedures

    VIEW 2 EXCERPTS

    2D-3D rigid registration of X-ray fluoroscopy and CT images using mutual information and sparsely sampled histogram estimators

    VIEW 2 EXCERPTS