# A Recursive Pyramidal Algorithm for Solving the Image Registration Problem

arXiv: https://arxiv.org/abs/2510.04231 · HTML: https://mlsanity.com/paper/2510.04231/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks](https://mlsanity.com/paper/1312.6229/) (2013)
- [Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2011.02910/) (2020)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Computing the Stereo Matching Cost with a Convolutional Neural Network](https://mlsanity.com/paper/1409.4326/) (2014)
- [Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching](https://mlsanity.com/paper/1708.09204/) (2017)
- [The Functional Correspondence Problem](https://mlsanity.com/paper/2109.01097/) (2021)
- [UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching](https://mlsanity.com/paper/2409.02545/) (2024)
- [Stereo Matching with Cost Volume based Sparse Disparity Propagation](https://mlsanity.com/paper/2201.11937/) (2022)

## Abstract (arXiv)

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.