# Text‐to‐Microstructure Generation Using Generative Deep Learning

https://mdr.nims.go.jp/datasets/15bfc8f2-a582-4bcf-a1b5-6871e31e414e

## File

- [Zheng_Small2024.pdf](https://mdr.nims.go.jp/filesets/5b38c09b-7a9d-49c2-97d7-e1e5a7bb4a86/download) ([Detail](https://mdr.nims.go.jp/filesets/5b38c09b-7a9d-49c2-97d7-e1e5a7bb4a86.md))

## Id

15bfc8f2-a582-4bcf-a1b5-6871e31e414e

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2024-09-19T07:13:27.667310Z

## Updated at

2024-09-19T23:30:21.049613Z

## Published at

2024-09-19T23:30:21.125870Z

## Doi



## First published url

https://doi.org/10.1002/smll.202402685

## Date published

2024-05-21

## Recorded date published

2024-9

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: Text‐to‐Microstructure Generation Using Generative Deep Learning
  title_type: original
  lang: en

## Description

- description: Designing novel materials is greatly dependent on understanding the
    design principles, physical mechanisms, and modeling methods of material microstructures,
    requiring experienced designers with expertise and several rounds of trial and
    error. Although recent advances in deep generative networks have enabled the inverse
    design of material microstructures, most studies involve property-conditional
    generation and focus on a specific type of structure, resulting in limited generation
    diversity and poor human--computer interaction. In this study, we proposed a pioneering
    text-to-microstructure deep generative network (Txt2Microstruct-Net) that enabled
    the generation of three-dimensional material microstructures directly from text
    prompts without additional optimization procedures. The Txt2Microstruct-Net model
    was trained on a large microstructure-caption paired dataset that was extensible
    using the algorithms provided. Moreover, the model was sufficiently flexible to
    generate different geometric representations, such as voxels and point clouds.
    The model's performance was also demonstrated in the inverse design of material
    microstructures and metamaterials. It has promising potential for interactive
    microstructure design when associated with large language models and could be
    a user-friendly tool for material design and discovery.
  description_type: abstract
  lang: und

## Creator

- name: Xiaoyang Zheng
  role: author
  orcid: https://orcid.org/0000-0003-1452-5855
- name: Ikumu Watanabe
  role: author
  orcid: https://orcid.org/0000-0002-7693-1675
- name: Jamie Paik
  role: author
  orcid: https://orcid.org/0000-0003-3869-213X
- name: Jingjing Li
  role: author
  orcid: https://orcid.org/0000-0002-6524-3105
- name: Xiaofeng Guo
  role: author
  orcid: https://orcid.org/0000-0003-1971-7442
- name: Masanobu Naito
  role: author
  orcid: https://orcid.org/0000-0001-7198-819X

## Contact agent



## Publisher

organization: Wiley

## Managing organization



## Keyword

- subject: microstructure generation
  schema: not_defined
- subject: deep learning
  schema: not_defined
- subject: natural language processing
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Small
  issn: '16136810'
  volume: '20'
  article_number: '2402685'

## Conference



## Related item



## Funding

- identifier: 22KJ0407
  funder_name: Japan Society for the Promotion of Science
- identifier: JP EG special 032023 11
  funder_name: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen
    Forschung

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 5b38c09b-7a9d-49c2-97d7-e1e5a7bb4a86
  filename: Zheng_Small2024.pdf
  content_type: application/pdf
  size: 3959211
  md5: 065775f8d3a1ab79a8e4f0303b2b5cf9

## Thumbnail

fileset_id: 5b38c09b-7a9d-49c2-97d7-e1e5a7bb4a86
filename: Zheng_Small2024.pdf