# Multiphase Reconstruction of Heterogeneous Materials Using Machine Learning and Quality of Connection Function

## TL;DR

This paper introduces a machine learning method to accurately reconstruct 3D material structures from 2D images, improving structure-property understanding.

## Contribution

A novel method using convolutional occupancy networks and QCF optimization for precise 3D microstructure reconstruction.

## Key findings

- The model successfully reconstructs 3D microstructures from 2D serial images.
- It outperforms existing methods like screened Poisson and local implicit grid approaches.
- The method supports isotropic and anisotropic materials with two or three phases.

## Abstract

Establishing accurate structure–property linkages and precise phase volume accuracy in 3D microstructure reconstruction of materials remains challenging, particularly with limited samples. This paper presents an optimized method for reconstructing 3D microstructures of various materials, including isotropic and anisotropic types with two and three phases, using convolutional occupancy networks and point clouds from inner layers of the microstructure. The method emphasizes precise phase representation and compatibility with point cloud data. A stage within the Quality of Connection Function (QCF) repetition loop optimizes the weights of the convolutional occupancy networks model to minimize error between the microstructure’s statistical properties and the reconstructive model. This model successfully reconstructs 3D representations from initial 2D serial images. Comparisons with screened Poisson surface reconstruction and local implicit grid methods demonstrate the model’s efficacy. The developed model proves suitable for high-quality 3D microstructure reconstruction, aiding in structure–property linkages and finite element analysis.