# Making Affine Correspondences Work in Camera Geometry Computation

arXiv: https://arxiv.org/abs/2007.10032 · HTML: https://mlsanity.com/paper/2007.10032/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 13 of 13)

- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Steerers: A framework for rotation equivariant keypoint descriptors](https://mlsanity.com/paper/2312.02152/) (2023)
- [A Large Scale Homography Benchmark](https://mlsanity.com/paper/2302.09997/) (2023)
- [Affine Correspondences between Multi-Camera Systems for Relative Pose Estimation](https://mlsanity.com/paper/2306.12996/) (2023)
- [Six-Point Method for Multi-Camera Systems with Reduced Solution Space](https://mlsanity.com/paper/2402.18066/) (2024)
- [Relative Pose from SIFT Features](https://mlsanity.com/paper/2203.07930/) (2022)
- [Affine steerers for structured keypoint description](https://mlsanity.com/paper/2408.14186/) (2024)
- [AffineGlue: Joint Matching and Robust Estimation](https://mlsanity.com/paper/2307.15381/) (2023)
- [Learning Affine Correspondences by Integrating Geometric Constraints](https://mlsanity.com/paper/2504.04834/) (2025)
- [On Relative Pose Recovery for Multi-Camera Systems](https://mlsanity.com/paper/2102.11996/) (2021)
- [Learning and Crafting for the Wide Multiple Baseline Stereo](https://mlsanity.com/paper/2112.12027/) (2021)
- [Rolling Shutter Relative Pose Estimation Made Practical](https://mlsanity.com/paper/2606.26863/) (2026)
- [Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features](https://mlsanity.com/paper/2608.20056/) (2026)

## Abstract (arXiv)

Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography, essential and fundamental matrix estimation. The main advantage of such solvers is that their sample size is smaller, e.g., only two instead of four matches are required to estimate a homography. Works proposing such solvers often claim a significant improvement in run-time thanks to fewer RANSAC iterations. We show that this argument is not valid in practice if the solvers are used naively. To overcome this, we propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. We propose a method for refining the local feature geometries by symmetric intensity-based matching, combine uncertainty propagation inside RANSAC with preemptive model verification, show a general scheme for computing uncertainty of minimal solvers results, and adapt the sample cheirality check for homography estimation. Our experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times when following our guidelines. We make code available at https://github.com/danini/affine-correspondences-for-camera-geometry.