Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion

计算机科学 维数之咒 体素 集合(抽象数据类型) 钥匙(锁) 人工智能 模式识别(心理学) 图像(数学) 体积热力学 构造(python库) 数据挖掘 计算机安全 量子力学 物理 程序设计语言
作者
Steve Kench,Samuel J. Cooper
出处
期刊:Nature Machine Intelligence [Springer Nature]
卷期号:3 (4): 299-305 被引量:144
标识
DOI:10.1038/s42256-021-00322-1
摘要

Generative adversarial networks (GANs) can be trained to generate three-dimensional (3D) image data, which are useful for design optimization. However, this conventionally requires 3D training data, which are challenging to obtain. Two-dimensional (2D) imaging techniques tend to be faster, higher resolution, better at phase identification and more widely available. Here we introduce a GAN architecture, SliceGAN, that is able to synthesize high-fidelity 3D datasets using a single representative 2D image. This is especially relevant for the task of material microstructure generation, as a cross-sectional micrograph can contain sufficient information to statistically reconstruct 3D samples. Our architecture implements the concept of uniform information density, which ensures both that generated volumes are equally high quality at all points in space and that arbitrarily large volumes can be generated. SliceGAN has been successfully trained on a diverse set of materials, demonstrating the widespread applicability of this tool. The quality of generated micrographs is shown through a statistical comparison of synthetic and real datasets of a battery electrode in terms of key microstructural metrics. Finally, we find that the generation time for a 108 voxel volume is on the order of a few seconds, yielding a path for future studies into high-throughput microstructural optimization. A generative approach called SliceGAN is demonstrated that can construct complex three-dimensional (3D) images from representative two-dimensional (2D) image examples. This is a promising approach in particular for studying microstructured materials where acquiring good-quality 3D data is challenging; 3D datasets can be created with SliceGAN, making use of high-quality 2D imaging techniques that are widely available.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
zxl完成签到,获得积分10
1秒前
Yangyang应助李剑鸿采纳,获得400
1秒前
1秒前
霍霍完成签到 ,获得积分10
2秒前
勤恳的白玉完成签到,获得积分10
2秒前
乐乐应助tangyuan采纳,获得10
2秒前
2秒前
无奈的焦完成签到,获得积分10
3秒前
bella完成签到 ,获得积分10
4秒前
Crystal完成签到,获得积分10
4秒前
5秒前
爆米花应助eyeland采纳,获得10
7秒前
桐桐应助U2采纳,获得10
7秒前
tuanheqi应助高高帅哥采纳,获得50
7秒前
Singularity应助科研通管家采纳,获得20
8秒前
科研通AI2S应助科研通管家采纳,获得30
8秒前
Lucas应助科研通管家采纳,获得10
8秒前
科目三应助七柚采纳,获得10
8秒前
隐形曼青应助科研通管家采纳,获得10
8秒前
Singularity应助科研通管家采纳,获得10
8秒前
顾矜应助科研通管家采纳,获得10
8秒前
共享精神应助科研通管家采纳,获得10
8秒前
9秒前
10秒前
10秒前
10秒前
大个应助淡定从凝采纳,获得10
10秒前
12秒前
12秒前
勤奋黑猫完成签到,获得积分10
12秒前
12秒前
乐乐应助龚成霖采纳,获得10
12秒前
hui发布了新的文献求助10
13秒前
TINA发布了新的文献求助10
13秒前
淡定的凡蕾完成签到,获得积分10
13秒前
14秒前
高贵背包应助yining采纳,获得10
15秒前
dongdong完成签到,获得积分10
15秒前
16秒前
仇悦发布了新的文献求助10
17秒前
高分求助中
Sustainability in ’Tides Chemistry 2000
Sustainability in ’Tides Chemistry 1500
The ACS Guide to Scholarly Communication 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Ethnicities: Media, Health, and Coping 800
Treatise on Geomorphology(2nd Edition - March 1, 2022) 520
Gerard de Lairesse : an artist between stage and studio 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3070075
求助须知:如何正确求助?哪些是违规求助? 2724068
关于积分的说明 7483773
捐赠科研通 2371206
什么是DOI,文献DOI怎么找? 1257323
科研通“疑难数据库(出版商)”最低求助积分说明 609889
版权声明 596879