3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks

TL;DR

This paper introduces an automated deep learning-based method for 3D reconstruction of curvilinear structures, specifically dislocations in microscopy images, eliminating the need for shape priors and reducing human intervention.

Contribution

It presents a fully automated pipeline using CNNs for detection and matching of curvilinear structures in stereo images, advancing 3D reconstruction without prior shape assumptions.

Findings

Automated detection and matching of dislocations in stereo TEM images.

Accurate 3D reconstruction of dislocations without shape priors.

Reduction of human intervention in 3D structural analysis.

Abstract

Curvilinear structures frequently appear in microscopy imaging as the object of interest. Crystallographic defects, i.e., dislocations, are one of the curvilinear structures that have been repeatedly investigated under transmission electron microscopy (TEM) and their 3D structural information is of great importance for understanding the properties of materials. 3D information of dislocations is often obtained by tomography which is a cumbersome process since it is required to acquire many images with different tilt angles and similar imaging conditions. Although, alternative stereoscopy methods lower the number of required images to two, they still require human intervention and shape priors for accurate 3D estimation. We propose a fully automated pipeline for both detection and matching of curvilinear structures in stereo pairs by utilizing deep convolutional neural networks (CNNs) without making any prior assumption on 3D shapes. In this work, we mainly focus on 3D reconstruction of dislocations from stereo pairs of TEM images.