Publication:
Inpainting of Ring Artifacts on Microtomographic Images by 3D CNN

Простая страница элемента
dc.contributor.authorYakimchuk, I.
dc.contributor.authorKornilov, A.
dc.contributor.authorSafonov, I.
dc.contributor.authorКорнилов, Антон Сергеевич
dc.contributor.authorСафонов, Илья Владимирович
dc.date.accessioned2024-11-26T13:39:09Z
dc.date.available2024-11-26T13:39:09Z
dc.date.issued2020
dc.description.abstract© 2020 FRUCT.Ring artifacts are inevitable in microtomographic images. In a Digital Rock workflow, such defects might affect the subsequent segmentation and flow simulation. We propose a correction of ring artifacts in reconstructed microtomographic images by inpainting. Our blind inpainting method uses a 3D convolutional network U-net. For the creation of training and validation datasets, we suggest an algorithm for transferring real ring artifacts to an arbitrary place in the undistorted slices of 8 big images of sandstones and sand. The parameters of the deep neural network and loss functions are analyzed. A loss function based on the multi-scale structural similarity index (MS-SSIM) allows to achieve the best performance. The developed solution corrects ring artifacts perfectly from a point of view of visual assessment and outperforms existing inpainting methods according to quality metrics based on MS-SSIM and mean absolute error (MAE).
dc.format.extentС. 200-206
dc.identifier.citationYakimchuk, I. Inpainting of Ring Artifacts on Microtomographic Images by 3D CNN / Yakimchuk, I., Kornilov, A., Safonov, I. // Conference of Open Innovation Association, FRUCT. - 2020. - 2020-April. - P. 200-206. - 10.23919/FRUCT48808.2020.9087422
dc.identifier.doi10.23919/FRUCT48808.2020.9087422
dc.identifier.urihttps://www.doi.org/10.23919/FRUCT48808.2020.9087422
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85085017841&origin=resultslist
dc.identifier.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000590125300028
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/21814
dc.relation.ispartofConference of Open Innovation Association, FRUCT
dc.titleInpainting of Ring Artifacts on Microtomographic Images by 3D CNN
dc.typeConference Paper
dspace.entity.typePublication
oaire.citation.volume2020-April
relation.isAuthorOfPublication1a1847b0-e43f-4541-9650-52e61b2bc844
relation.isAuthorOfPublicationbea4aa08-ff8b-4593-a47b-2d560090fba8
relation.isAuthorOfPublication.latestForDiscovery1a1847b0-e43f-4541-9650-52e61b2bc844
relation.isOrgUnitOfPublicationd19559ab-04cd-486a-ae8e-f40ccd36a1a6
relation.isOrgUnitOfPublication.latestForDiscoveryd19559ab-04cd-486a-ae8e-f40ccd36a1a6
Файлы
Коллекции
Публикации