# Relative Pose from SIFT Features

arXiv: https://arxiv.org/abs/2203.07930 · HTML: https://mlsanity.com/paper/2203.07930/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [Graph-Cut RANSAC](https://mlsanity.com/paper/1706.00984/) (2017)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [MODS: Fast and Robust Method for Two-View Matching](https://mlsanity.com/paper/1503.02619/) (2015)
- [A clever elimination strategy for efficient minimal solvers](https://mlsanity.com/paper/1703.05289/) (2017)
- [A Minimal Solution for Two-view Focal-length Estimation using Two Affine Correspondences](https://mlsanity.com/paper/1706.01649/) (2017)
- [Making Affine Correspondences Work in Camera Geometry Computation](https://mlsanity.com/paper/2007.10032/) (2020)
- [Five-point Fundamental Matrix Estimation for Uncalibrated Cameras](https://mlsanity.com/paper/1803.00260/) (2018)
- [Radially-Distorted Conjugate Translations](https://mlsanity.com/paper/1711.11339/) (2017)
- [Homography from two orientation- and scale-covariant features](https://mlsanity.com/paper/1906.11927/) (2019)
- [Rectification from Radially-Distorted Scales](https://mlsanity.com/paper/1807.06110/) (2018)
- [Recovering affine features from orientation- and scale-invariant ones](https://mlsanity.com/paper/1807.03503/) (2018)

## Built on by (most cited first, 6 of 6)

- [Steerers: A framework for rotation equivariant keypoint descriptors](https://mlsanity.com/paper/2312.02152/) (2023)
- [IMP: Iterative Matching and Pose Estimation with Adaptive Pooling](https://mlsanity.com/paper/2304.14837/) (2023)
- [RePoseD: Efficient Relative Pose Estimation With Known Depth Information](https://mlsanity.com/paper/2501.07742/) (2025)
- [Handbook on Leveraging Lines for Two-View Relative Pose Estimation](https://mlsanity.com/paper/2309.16040/) (2023)
- [VisIRNet: Deep Image Alignment for UAV-taken Visible and Infrared Image Pairs](https://mlsanity.com/paper/2402.09635/) (2024)
- [Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features](https://mlsanity.com/paper/2608.20056/) (2026)

## Abstract (arXiv)

This paper proposes the geometric relationship of epipolar geometry and orientation- and scale-covariant, e.g., SIFT, features. We derive a new linear constraint relating the unknown elements of the fundamental matrix and the orientation and scale. This equation can be used together with the well-known epipolar constraint to, e.g., estimate the fundamental matrix from four SIFT correspondences, essential matrix from three, and to solve the semi-calibrated case from three correspondences. Requiring fewer correspondences than the well-known point-based approaches (e.g., 5PT, 6PT and 7PT solvers) for epipolar geometry estimation makes RANSAC-like randomized robust estimation significantly faster. The proposed constraint is tested on a number of problems in a synthetic environment and on publicly available real-world datasets on more than 80000 image pairs. It is superior to the state-of-the-art in terms of processing time while often leading to more accurate results.