用少量代码和数据实现高精度图像配准，适合资源受限场景。
A Recursive Pyramidal Algorithm for Solving the Image Registration Problem
- 递归金字塔结构，端到端可训练
- 仅74张图像+19x15输入窗口即达高精度
- 代码简洁（十余行），适合低资源应用
图像配准旨在寻找一个变换，使两幅图像的对应点重合。本文提出一种简单、端到端可训练的算法，仅需少量代码即可实现。该方法在极少训练数据与时间下表现良好，部分场景下精度优异。以立体视觉为例，仅用74张图像和19x15输入窗口即可完成训练。十余行Python代码即实现高效配准，具有极简性，适用于训练数据、时间或代码复杂度受限的场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。