Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/43B46NS
Repositorysid.inpe.br/sibgrapi/2020/09.27.23.55
Last Update2020:09.27.23.55.47 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2020/09.27.23.55.47
Metadata Last Update2022:06.14.00.00.08 (UTC) administrator
DOI10.1109/SIBGRAPI51738.2020.00040
Citation KeyBarrientosFernFern:2020:ReImIn
TitleA review on image inpainting techniques and datasets
FormatOn-line
Year2020
Access Date2024, May 02
Number of Files1
Size4713 KiB
2. Context
Author1 Barrientos, David
2 Fernandes, Bruno
3 Fernandes, Sergio
Affiliation1 Universidade de Pernambuco, Brasil
2 Universidade de Pernambuco, Brasil
3 Universidade de Pernambuco, Brasil
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
e-Mail Addressdjbr@ecomp.poli.br
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationPorto de Galinhas (virtual)
Date7-10 Nov. 2020
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2020-09-27 23:55:47 :: djbr@ecomp.poli.br -> administrator ::
2022-06-14 00:00:08 :: administrator -> djbr@ecomp.poli.br :: 2020
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsconvolution-based
dataset
deep-learning
diffusion-based
inpainting
patch-based
reconstruction
AbstractImage inpainting is a process that allows filling in target regions with alternative contents by estimating the suitable information from auxiliary data, either from surrounding areas or external sources. Digital image inpainting techniques are classified in traditional techniques and Deep Learning techniques. Traditional techniques are able to produce accurate high-quality results when the missing areas are small, however none of them are able to generate novel objects not found in the source image neither to produce semantically consistent results. Deep Learning techniques have greatly improved the quality on image inpainting delivering promising results by generating semantic hole filling and novel objects not found in the original image. However, there is still a lot of room for improvement, specially on arbitrary image sizes, arbitrary masks, high resolution texture synthesis, reduction of computation resources and reduction of training time. This work classifies and orders chronologically the most prominent techniques, providing an overall explanation on its operation. It presents, as well, the most used datasets and evaluation metrics across all the works reviewed.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2020 > A review on...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > A review on...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 27/09/2020 20:55 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/43B46NS
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/43B46NS
Languageen
Target File89 - A Review on Image Inpainting Techniques and Datasets.pdf
User Groupdjbr@ecomp.poli.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/43G4L9S
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2020/10.28.20.46 5
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume
7. Description control
e-Mail (login)djbr@ecomp.poli.br
update 


Close