Multiview 2D/3D Rigid Registration viaa Point-Of-Interest Network for Tracking and Triangulation
Abstract
We propose to tackle the multiview 2D/3D rigid registration problem via a Point-Of-Interest Network for Tracking and Triangulation (POINT2
). POINT2
learns to establish 2D point-to-point correspondences between the preand intra-intervention images by tracking a set of pointof-interests (POIs). The 3D pose of the pre-intervention
volume is then estimated through a triangulation layer. In
POINT2
, the unified framework of the POI tracker and the
triangulation layer enables learning informative 2D features and estimating 3D pose jointly. In contrast to existing
approaches, POINT2 only requires a single forward-pass to
achieve a reliable 2D/3D registration. As the POI tracker
is shift-invariant, POINT2
is more robust to the initial pose
of the 3D pre-intervention image. Extensive experiments
on a large-scale clinical cone-beam computed tomography
dataset show that the proposed POINT2 method outperforms the existing learning-based method in terms of accuracy, robustness and running time. Furthermore, when used
as an initial pose estimator, our method also improves the
robustness and speed of the state-of-the-art optimizationbased approaches by ten folds.