Saved in:
Bibliographic Details
Main Author: Dirnstorfer, Stefan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.04231
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915533823148032
author Dirnstorfer, Stefan
author_facet Dirnstorfer, Stefan
contents The problem of image registration is finding a transformation that aligns two images, such that the corresponding points are in the same location. This paper introduces a simple, end-to-end trainable algorithm that is implementable in a few lines of Python code. The approach is shown to work with very little training data and training time, while achieving accurate results in some settings. An example application to stereo vision was trained from 74 images on a 19x15 input window. With just a dozen lines of Python code this algorithm excels in brevity and may serve as a good start in related scenarios with limitations to training data, training time or code complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04231
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Recursive Pyramidal Algorithm for Solving the Image Registration Problem
Dirnstorfer, Stefan
Computer Vision and Pattern Recognition
The problem of image registration is finding a transformation that aligns two images, such that the corresponding points are in the same location. This paper introduces a simple, end-to-end trainable algorithm that is implementable in a few lines of Python code. The approach is shown to work with very little training data and training time, while achieving accurate results in some settings. An example application to stereo vision was trained from 74 images on a 19x15 input window. With just a dozen lines of Python code this algorithm excels in brevity and may serve as a good start in related scenarios with limitations to training data, training time or code complexity.
title A Recursive Pyramidal Algorithm for Solving the Image Registration Problem
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.04231