New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence

Abstract

A fundamental open problem in computer vision-determining pose and correspondence between two sets of points in space(cid:173) is solved with a novel, robust and easily implementable algorithm. The technique works on noisy point sets that may be of unequal sizes and may differ by non-rigid transformations. A 2D varia(cid:173) tion calculates the pose between point sets related by an affine transformation-translation, rotation, scale and shear. A 3D to 3D variation calculates translation and rotation. An objective describ(cid:173) ing the problem is derived from Mean field theory. The objective is minimized with clocked (EM-like) dynamics. Experiments with both handwritten and synthetic data provide empirical evidence for the method.

Cite

Text

Gold et al. "New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence." Neural Information Processing Systems, 1994.

Markdown

[Gold et al. "New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/gold1994neurips-new/)

BibTeX

@inproceedings{gold1994neurips-new,
  title     = {{New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence}},
  author    = {Gold, Steven and Lu, Chien-Ping and Rangarajan, Anand and Pappu, Suguna and Mjolsness, Eric},
  booktitle = {Neural Information Processing Systems},
  year      = {1994},
  pages     = {957-964},
  url       = {https://mlanthology.org/neurips/1994/gold1994neurips-new/}
}