A Decade of Generative Adversarial Networks for Porous Material Reconstruction

2026-03-12

AI Summary

This study addresses the critical challenge of digital reconstruction of porous materials—essential in geological reservoirs, tissue engineering, and electrochemical devices—where conventional methods are constrained by limitations in accuracy, efficiency, and scalability. Surveying 96 publications from 2017 to 2026, this work proposes the first comprehensive taxonomy of generative adversarial network (GAN) architectures for porous media reconstruction, categorizing them into six classes: Vanilla, multi-scale, conditional, attention-enhanced, Style-based, and hybrid GANs. The review demonstrates remarkable advances: reconstruction resolution has escalated from 64³ to 2200³ voxels, porosity error is maintained below 1%, average relative error in permeability prediction is reduced by 79%, and reconstructed volume has increased by over 40,000-fold, substantially advancing high-fidelity, large-scale generation of porous structures.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Digital reconstruction of porous materials has become increasingly critical for applications ranging from geological reservoir characterization to tissue engineering and electrochemical device design. While traditional methods such as micro-computed tomography and statistical reconstruction approaches have established foundations in this field, the emergence of deep learning techniques, particularly Generative Adversarial Networks (GANs), has revolutionized porous media reconstruction capabilities. This review systematically analyzes 96 peer-reviewed articles published from 2017 to early 2026, examining the evolution and applications of GAN-based approaches for porous material image reconstruction. We categorize GAN architectures into six distinct classes, namely Vanilla GANs, Multi-Scale GANs, Conditional GANs, Attention-Enhanced GANs, Style-based GANs, and Hybrid Architecture GANs. Our analysis reveals substantial progress including improvements in porosity accuracy (within 1% of original samples), permeability prediction (up to 79% reduction in mean relative errors), and achievable reconstruction volumes (from initial $64^3$ to current $2{,}200^3$ voxels). Despite these advances, persistent challenges remain in computational efficiency, memory constraints for large-scale reconstruction, and maintaining structural continuity in 2D-to-3D transformations. This systematic analysis provides a comprehensive framework for selecting appropriate GAN architectures based on specific application requirements.

Problem

• porous material reconstruction
• digital reconstruction
• structural continuity
• computational efficiency
• large-scale reconstruction

Innovation

• Generative Adversarial Networks
• Porous Material Reconstruction
• Digital Microstructure
• Deep Learning
• 3D Image Synthesis