# Affine Correspondences in Stereo Vision: Theory, Practice, and Limitations

arXiv: https://arxiv.org/abs/2603.01836 · HTML: https://mlsanity.com/paper/2603.01836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 5 of 5)

- [A Minimal Solution for Two-view Focal-length Estimation using Two Affine Correspondences](https://mlsanity.com/paper/1706.01649/) (2017)
- [Minimal Solutions for Relative Pose with a Single Affine Correspondence](https://mlsanity.com/paper/1912.10776/) (2019)
- [Relative planar motion for vehicle-mounted cameras from a single affine correspondence](https://mlsanity.com/paper/1912.06465/) (2019)
- [P1AC: Revisiting Absolute Pose From a Single Affine Correspondence](https://mlsanity.com/paper/2011.08790/) (2020)
- [Least-squares Optimal Relative Planar Motion for Vehicle-mounted Cameras](https://mlsanity.com/paper/1912.06464/) (2019)

## Abstract (arXiv)

Affine transformations have been recently used for stereo vision. They can be exploited in various computer vision application, e.g., when estimating surface normals, homographies, fundamental and essential matrices. Even full 3D reconstruction can be obtained by using affine correspondences. First, this paper overviews the fundamental statements for affine transformations and epipolar geometry. Then it is investigated how the transformation accuracy influences the quality of the 3D reconstruction. Besides, we propose novel techniques for estimating the local affine transformation from corresponding image directions; moreover, the fundamental matrix, related to the processed image pair, can also be exploited. Both synthetic and real quantitative evaluations are implemented based on the accuracy of the reconstructed surface normals. For the latter one, a special object, containing three perpendicular planes with chessboard patterns, is constructed. The quantitative evaluations are based on the accuracy of the reconstructed surface normals and it is concluded that the estimation accuracy is around a few degrees for realistic test cases. Special stereo poses and plane orientations are also evaluated in detail.