3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks
This addresses the cumbersome and manual process of obtaining 3D information for materials science applications, offering an incremental improvement over existing stereoscopy methods.
The paper tackles the problem of 3D reconstruction of curvilinear structures like dislocations in microscopy by proposing a fully automated pipeline using deep CNNs for detection and matching in stereo pairs, eliminating the need for human intervention and shape priors.
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.