Unsupervised Difference Learning for Noisy Rigid Image Alignment

TL;DR

This paper introduces an unsupervised difference learning approach that improves rigid image alignment accuracy in noisy conditions by converting the problem into a pseudo supervised task, outperforming traditional methods.

Contribution

The paper proposes a novel UDL strategy for unsupervised rigid image alignment that enhances noise robustness and accuracy, especially for noisy images, by leveraging regression properties.

Findings

Accurately estimates rotation on noisy and clean images

Effective in natural and cryo-EM image datasets

Outperforms traditional unsupervised alignment methods

Abstract

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer networks show an improved performance on clean images but will not achieve satisfactory performance on noisy images due to its heavy reliance on pixel value comparations. To handle such challenging applications, we report a new unsupervised difference learning (UDL) strategy and apply it to rigid image alignment. UDL exploits the quantitative properties of regression tasks and converts the original unsupervised problem to pseudo supervised problem. Under the new UDL-based image alignment pipeline, rotation can be accurately estimated on both clean and noisy images and translations can then be easily solved. Experimental results on both nature and cryo-EM images demonstrate the efficacy of our UDL-based unsupervised rigid image alignment method.