No Cover Image

E-Thesis 334 views

Computer Vision-based Microstructure Reconstruction of Heterogeneous / XIANGYUN GE

Swansea University Author: XIANGYUN GE

  • E-Thesis under embargo until: 12th February 2030

DOI (Published version): 10.23889/SUThesis.69222

Abstract

This thesis presents a novel approach to heterogeneous material microstructure image re-construction using AI-generated content (AIGC) methods based on computer vision (CV). By focusing on the unique challenges posed by heterogeneous material structures, this work optimizes network architectures to...

Full description

Published: Swansea University, Wales, UK 2025
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Neto, E. D. S., and Li, C.
URI: https://cronfa.swan.ac.uk/Record/cronfa69222
first_indexed 2025-04-03T14:57:07Z
last_indexed 2025-04-04T05:16:26Z
id cronfa69222
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-04-03T16:01:57.2391520</datestamp><bib-version>v2</bib-version><id>69222</id><entry>2025-04-03</entry><title>Computer Vision-based Microstructure Reconstruction of Heterogeneous</title><swanseaauthors><author><sid>c39ff918855a366c9266912315a176f9</sid><firstname>XIANGYUN</firstname><surname>GE</surname><name>XIANGYUN GE</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-04-03</date><abstract>This thesis presents a novel approach to heterogeneous material microstructure image re-construction using AI-generated content (AIGC) methods based on computer vision (CV). By focusing on the unique challenges posed by heterogeneous material structures, this work optimizes network architectures to enhance both the ef&#xFB01;ciency and accuracy of image generation. The research can be divided into three major contributions.First, the Statistically-Informed Neural Networks (SINN) method, originally designed for binary-phase porous media, is extended to multi-phase heterogeneous materials. This ex- tension broadens the applicability of the SINN approach, enabling more complex material reconstructions.Second, the explicit descriptor-based optimization techniques from traditional statistical reconstruction algorithms are incorporated into CV-based AI microstructure reconstruction methods. This integration ensures that the generated images not only match geometric pat- terns but also adhere closely to quantitative material descriptors, improving interpretability and precision.Third, improvements are made to existing CV-based generative models by tailoring them speci&#xFB01;cally to the task of heterogeneous material microstructure reconstruction. These improvements simplify the model structure and reduce the number of parameters while maintaining high accuracy in image generation.Ultimately, the combined methods lead to the &#xFB01;rst-ever conditional generative model capable of generating 3D images from 2D slice descriptors. The proposed model is validated throughcomparison with the state-of-the-art SliceGAN, demonstrating superior accuracy and ef&#xFB01;ciency through explicit optimization.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Image reconstruction, heterogeneous material, microstructure reconstruction</keywords><publishedDay>12</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-02-12</publishedDate><doi>10.23889/SUThesis.69222</doi><url/><notes>A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Neto, E. D. S., and Li, C.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>China Scholarship Council</degreesponsorsfunders><apcterm/><funders>China Scholarship Council</funders><projectreference/><lastEdited>2025-04-03T16:01:57.2391520</lastEdited><Created>2025-04-03T15:49:07.1273073</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering</level></path><authors><author><firstname>XIANGYUN</firstname><surname>GE</surname><order>1</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2025-04-03T15:55:47.1267286</uploaded><type>Output</type><contentLength>54333273</contentLength><contentType>application/pdf</contentType><version>E-Thesis</version><cronfaStatus>true</cronfaStatus><embargoDate>2030-02-12T00:00:00.0000000</embargoDate><documentNotes>Copyright: The Author, Xiangyun Ge, 2024 Distributed under the terms of a Creative Commons Attribution Non Commercial 4.0 License (CC BY-NC 4.0)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-04-03T16:01:57.2391520 v2 69222 2025-04-03 Computer Vision-based Microstructure Reconstruction of Heterogeneous c39ff918855a366c9266912315a176f9 XIANGYUN GE XIANGYUN GE true false 2025-04-03 This thesis presents a novel approach to heterogeneous material microstructure image re-construction using AI-generated content (AIGC) methods based on computer vision (CV). By focusing on the unique challenges posed by heterogeneous material structures, this work optimizes network architectures to enhance both the efficiency and accuracy of image generation. The research can be divided into three major contributions.First, the Statistically-Informed Neural Networks (SINN) method, originally designed for binary-phase porous media, is extended to multi-phase heterogeneous materials. This ex- tension broadens the applicability of the SINN approach, enabling more complex material reconstructions.Second, the explicit descriptor-based optimization techniques from traditional statistical reconstruction algorithms are incorporated into CV-based AI microstructure reconstruction methods. This integration ensures that the generated images not only match geometric pat- terns but also adhere closely to quantitative material descriptors, improving interpretability and precision.Third, improvements are made to existing CV-based generative models by tailoring them specifically to the task of heterogeneous material microstructure reconstruction. These improvements simplify the model structure and reduce the number of parameters while maintaining high accuracy in image generation.Ultimately, the combined methods lead to the first-ever conditional generative model capable of generating 3D images from 2D slice descriptors. The proposed model is validated throughcomparison with the state-of-the-art SliceGAN, demonstrating superior accuracy and efficiency through explicit optimization. E-Thesis Swansea University, Wales, UK Image reconstruction, heterogeneous material, microstructure reconstruction 12 2 2025 2025-02-12 10.23889/SUThesis.69222 A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information COLLEGE NANME COLLEGE CODE Swansea University Neto, E. D. S., and Li, C. Doctoral Ph.D China Scholarship Council China Scholarship Council 2025-04-03T16:01:57.2391520 2025-04-03T15:49:07.1273073 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering XIANGYUN GE 1 Under embargo Under embargo 2025-04-03T15:55:47.1267286 Output 54333273 application/pdf E-Thesis true 2030-02-12T00:00:00.0000000 Copyright: The Author, Xiangyun Ge, 2024 Distributed under the terms of a Creative Commons Attribution Non Commercial 4.0 License (CC BY-NC 4.0) true eng https://creativecommons.org/licenses/by-nc/4.0/
title Computer Vision-based Microstructure Reconstruction of Heterogeneous
spellingShingle Computer Vision-based Microstructure Reconstruction of Heterogeneous
XIANGYUN GE
title_short Computer Vision-based Microstructure Reconstruction of Heterogeneous
title_full Computer Vision-based Microstructure Reconstruction of Heterogeneous
title_fullStr Computer Vision-based Microstructure Reconstruction of Heterogeneous
title_full_unstemmed Computer Vision-based Microstructure Reconstruction of Heterogeneous
title_sort Computer Vision-based Microstructure Reconstruction of Heterogeneous
author_id_str_mv c39ff918855a366c9266912315a176f9
author_id_fullname_str_mv c39ff918855a366c9266912315a176f9_***_XIANGYUN GE
author XIANGYUN GE
author2 XIANGYUN GE
format E-Thesis
publishDate 2025
institution Swansea University
doi_str_mv 10.23889/SUThesis.69222
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering
document_store_str 0
active_str 0
description This thesis presents a novel approach to heterogeneous material microstructure image re-construction using AI-generated content (AIGC) methods based on computer vision (CV). By focusing on the unique challenges posed by heterogeneous material structures, this work optimizes network architectures to enhance both the efficiency and accuracy of image generation. The research can be divided into three major contributions.First, the Statistically-Informed Neural Networks (SINN) method, originally designed for binary-phase porous media, is extended to multi-phase heterogeneous materials. This ex- tension broadens the applicability of the SINN approach, enabling more complex material reconstructions.Second, the explicit descriptor-based optimization techniques from traditional statistical reconstruction algorithms are incorporated into CV-based AI microstructure reconstruction methods. This integration ensures that the generated images not only match geometric pat- terns but also adhere closely to quantitative material descriptors, improving interpretability and precision.Third, improvements are made to existing CV-based generative models by tailoring them specifically to the task of heterogeneous material microstructure reconstruction. These improvements simplify the model structure and reduce the number of parameters while maintaining high accuracy in image generation.Ultimately, the combined methods lead to the first-ever conditional generative model capable of generating 3D images from 2D slice descriptors. The proposed model is validated throughcomparison with the state-of-the-art SliceGAN, demonstrating superior accuracy and efficiency through explicit optimization.
published_date 2025-02-12T05:27:35Z
_version_ 1851097828317724672
score 11.089386

Similar Items