Fast and Accurate 3D Registration from Line Intersection Constraints

    •  Mateus, A., Ranade, S., Ramalingam, S., Miraldo, P., "Fast and Accurate 3D Registration from Line Intersection Constraints", International Journal of Computer Vision, DOI: 10.1007/​s11263-023-01774-1, Vol. 131, pp. 2044-2069, February 2023.
      BibTeX TR2023-007 PDF
      • @article{Mateus2023feb,
      • author = {Mateus, Andre and Ranade, Siddhant and Ramalingam, Srikumar and Miraldo, Pedro},
      • title = {Fast and Accurate 3D Registration from Line Intersection Constraints},
      • journal = {International Journal of Computer Vision},
      • year = 2023,
      • volume = 131,
      • pages = {2044--2069},
      • month = feb,
      • doi = {10.1007/s11263-023-01774-1},
      • url = {}
      • }
  • MERL Contact:
  • Research Area:

    Computer Vision


3D Registration is a fundamental part of several robotics and automation tasks. While classical methods predominantly exploit constraints from points or plane correspondences, we have a dif- ferent take using line intersections. In other words, we focus on exploiting geometric constraints arising from the intersection of two (different) 3D line segments in two scans. In particular, we derive nine minimal solvers from various geometric constraints arising from line intersections along with other constraints: plane correspondences, point correspondences, and line matches. We fol- low a two-step method for 3D registration: a coarse estimation with outlier rejection followed by refinement. In the first step, we use a hybrid RANSAC loop that utilizes all the minimal solvers. This RANSAC outputs a rough estimate for the 3D registration and the outlier/inlier classification for the 3D features. As for the refinement, we offer a non-linear technique using all the inliers obtained from the RANSAC and the coarse estimate. This method is of alternate minimization type, in which we alternate between estimating the rotation and the translation at each step. Thorough experiments with simulated data and two real-world datasets show that using these features and the combined solvers improves accuracy and is faster than the baselines.