M.C. Neves , J. Filgueiras , Z. Kokkinogenis , M.C.F. Silva , J.B.L.M. Campos , L.P. Reis
{"title":"利用生成式对抗网络的超分辨率提高两相气泡系统的实验图像质量","authors":"M.C. Neves , J. Filgueiras , Z. Kokkinogenis , M.C.F. Silva , J.B.L.M. Campos , L.P. Reis","doi":"10.1016/j.ijmultiphaseflow.2024.104952","DOIUrl":null,"url":null,"abstract":"<div><p>Fluid Dynamics is a key scientific field to multitudes of engineering applications. Experimental work in this field requires careful set-up and expensive image-capturing equipment, particularly when considering the finer details of complex phenomena. In this work, we study the application of super-resolution Generative Adversarial Networks (GANs) to achieve high-resolution results by upscaling lower-resolution experimental images.</p><p>We train GANs proposed for natural images on a bubbly flow experimental Fluid Dynamics dataset and compare common super-resolution evaluation metrics to domain expert assessments of the upscaled images. We find that these models achieve promising results, as evaluated by experts, and transfer learning from natural images translates to better performance overall. Attention mechanisms are found to be particularly useful in recreating sharper details. On the other hand, traditional super-resolution evaluation metrics are found to align poorly with expert perception of quality, signaling the need for better systematic evaluation methodologies in this domain.</p></div>","PeriodicalId":339,"journal":{"name":"International Journal of Multiphase Flow","volume":"180 ","pages":"Article 104952"},"PeriodicalIF":3.6000,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0301932224002295/pdfft?md5=1a4738b42f368e2ff305834dc8778e10&pid=1-s2.0-S0301932224002295-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Enhancing experimental image quality in two-phase bubbly systems with super-resolution using generative adversarial networks\",\"authors\":\"M.C. Neves , J. Filgueiras , Z. Kokkinogenis , M.C.F. Silva , J.B.L.M. Campos , L.P. Reis\",\"doi\":\"10.1016/j.ijmultiphaseflow.2024.104952\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Fluid Dynamics is a key scientific field to multitudes of engineering applications. Experimental work in this field requires careful set-up and expensive image-capturing equipment, particularly when considering the finer details of complex phenomena. In this work, we study the application of super-resolution Generative Adversarial Networks (GANs) to achieve high-resolution results by upscaling lower-resolution experimental images.</p><p>We train GANs proposed for natural images on a bubbly flow experimental Fluid Dynamics dataset and compare common super-resolution evaluation metrics to domain expert assessments of the upscaled images. We find that these models achieve promising results, as evaluated by experts, and transfer learning from natural images translates to better performance overall. Attention mechanisms are found to be particularly useful in recreating sharper details. On the other hand, traditional super-resolution evaluation metrics are found to align poorly with expert perception of quality, signaling the need for better systematic evaluation methodologies in this domain.</p></div>\",\"PeriodicalId\":339,\"journal\":{\"name\":\"International Journal of Multiphase Flow\",\"volume\":\"180 \",\"pages\":\"Article 104952\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2024-08-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0301932224002295/pdfft?md5=1a4738b42f368e2ff305834dc8778e10&pid=1-s2.0-S0301932224002295-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Multiphase Flow\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0301932224002295\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MECHANICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Multiphase Flow","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0301932224002295","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MECHANICS","Score":null,"Total":0}
Enhancing experimental image quality in two-phase bubbly systems with super-resolution using generative adversarial networks
Fluid Dynamics is a key scientific field to multitudes of engineering applications. Experimental work in this field requires careful set-up and expensive image-capturing equipment, particularly when considering the finer details of complex phenomena. In this work, we study the application of super-resolution Generative Adversarial Networks (GANs) to achieve high-resolution results by upscaling lower-resolution experimental images.
We train GANs proposed for natural images on a bubbly flow experimental Fluid Dynamics dataset and compare common super-resolution evaluation metrics to domain expert assessments of the upscaled images. We find that these models achieve promising results, as evaluated by experts, and transfer learning from natural images translates to better performance overall. Attention mechanisms are found to be particularly useful in recreating sharper details. On the other hand, traditional super-resolution evaluation metrics are found to align poorly with expert perception of quality, signaling the need for better systematic evaluation methodologies in this domain.
期刊介绍:
The International Journal of Multiphase Flow publishes analytical, numerical and experimental articles of lasting interest. The scope of the journal includes all aspects of mass, momentum and energy exchange phenomena among different phases such as occur in disperse flows, gas–liquid and liquid–liquid flows, flows in porous media, boiling, granular flows and others.
The journal publishes full papers, brief communications and conference announcements.