P2Pi: A Minimal Solution for Registration of 3D Points to 3D Planes

    •  Ramalingam, S., Taguchi, Y., Marks, T.K., Tuzel, O., "P2Pi: A Minimal Solution for Registration of 3D Points to 3D Planes", European Conference on Computer Vision (ECCV), September 2010.
      BibTeX TR2010-086 PDF
      • @inproceedings{Ramalingam2010sep,
      • author = {Ramalingam, S. and Taguchi, Y. and Marks, T.K. and Tuzel, O.},
      • title = {P2Pi: A Minimal Solution for Registration of 3D Points to 3D Planes},
      • booktitle = {European Conference on Computer Vision (ECCV)},
      • year = 2010,
      • month = sep,
      • isbn = {978-3-642-15554-3},
      • url = {}
      • }
  • MERL Contact:
  • Research Areas:

    Computer Vision, Robotics

TR Image

This paper presents a class of minimal solutions for the 3D-to-3D registration problem in which the sensor data are 3D points and the corresponding object data are 3D planes. In order to compare the 6 degrees-of-freedom transformation between the sensor and the object, we need at least six points on three or more planes. We systematically investigate and develop pose estimation algorithms for several configurations, including all minimal configurations, that arise from the distribution of points on planes. The degenerate configurations are also identified. We point out that many existing and unsolved 2D-to-3D and 3D-to-3D pose estimation algorithms involving points, lines, and planes can be transformed into the problem of registering points to planes. In addition to simulations, we also demonstrate the algorithm's effectiveness in two real-world applications: registration of a robotic arm with an object using a contact sensor, and registration of 3D point clouds that were obtained using multi-view reconstruction of planar city models.


  • Related News & Events

    •  NEWS    ECCV 2010: 5 publications by Yuichi Taguchi, Srikumar Ramalingam, Amit K. Agrawal, C. Oncel Tuzel and Tim K. Marks
      Date: September 5, 2010
      Where: European Conference on Computer Vision (ECCV)
      MERL Contact: Tim K. Marks
      Research Area: Computer Vision
      • The papers "Image Invariants for Smooth Reflective Surfaces" by Sankaranarayanan, A.C., Veeraraghavan, A., Tuzel, O. and Agrawal, A., "Analytical Forward Projection for Axial Non-Central Dioptric & Catadioptric Cameras" by Agrawal, A., Taguchi, Y. and Ramalingam, S., "P2Pi: A Minimal Solution for Registration of 3D Points to 3D Planes" by Ramalingam, S., Taguchi, Y., Marks, T.K. and Tuzel, O., "Fast Approximate Nearest Neighbor Methods for Non-Euclidean Manifolds with Applications to Human Activity Analysis in Videos" by Chaudhry, R. and Ivanov, Y. and "Flexible Voxels for Motion-Aware Videography" by Gupta, M., Agrawal, A., Veeraraghavan, A. and Narasimhan, S.G. were presented at the European Conference on Computer Vision (ECCV).