Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPAW/3RMMGU8
Repositorysid.inpe.br/sibgrapi/2018/08.25.02.07
Last Update2018:08.25.02.07.44 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2018/08.25.02.07.44
Metadata Last Update2022:06.14.00.09.06 (UTC) administrator
DOI10.1109/SIBGRAPI.2018.00014
Citation KeySouzaMaceNascOliv:2018:ReHiSp
TitleReal-Time High-Quality Specular Highlight Removal using Efficient Pixel Clustering
FormatOn-line
Year2018
Access Date2024, May 18
Number of Files1
Size1038 KiB
2. Context
Author1 Souza, Antonio Carlos dos Santos
2 Macedo, Márcio Cerqueira de Farias
3 Nascimento, Verônica Paixão do
4 Oliveira, Bruno Santos
Affiliation1 Federal Institute of Bahia
2 Federal University of Bahia
3 Federal Institute of Bahia
4 Computação Brasil
EditorRoss, Arun
Gastal, Eduardo S. L.
Jorge, Joaquim A.
Queiroz, Ricardo L. de
Minetto, Rodrigo
Sarkar, Sudeep
Papa, João Paulo
Oliveira, Manuel M.
Arbeláez, Pablo
Mery, Domingo
Oliveira, Maria Cristina Ferreira de
Spina, Thiago Vallin
Mendes, Caroline Mazetto
Costa, Henrique Sérgio Gutierrez
Mejail, Marta Estela
Geus, Klaus de
Scheer, Sergio
e-Mail Addressmarciocfmacedo@hotmail.com
Conference NameConference on Graphics, Patterns and Images, 31 (SIBGRAPI)
Conference LocationFoz do Iguaçu, PR, Brazil
Date29 Oct.-1 Nov. 2018
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2018-08-25 02:07:44 :: marciocfmacedo@hotmail.com -> administrator ::
2022-06-14 00:09:06 :: administrator -> :: 2018
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
KeywordsSpecular Highlight Removal
Real Time
Clustering
GPU
AbstractOn the basis of the dichromatic reflection model, recent specular highlight removal techniques typically estimate and cluster illumination chromaticity values to separate diffuse and specular reflection components from a single image. While these techniques are able to obtain visually pleasing results, their clustering algorithms suffer from bad initialization or are too costly to be computed in real time. In this paper, we propose a high-quality pixel clustering approach that allows the removal of specular highlights from a single image in real time. We follow previous work and estimate the minimum and maximum chromaticity values for every pixel. Then, we analyze the distribution pattern of those values in a minimum-maximum chromaticity space to propose an efficient pixel clustering approach. Afterwards, we estimate an intensity ratio for each cluster in order to separate diffuse and specular components. Finally, we present optimization strategies to implement our approach efficiently for both CPU and GPU architectures. Experimental results evaluated in the available dataset show that the proposed approach is not only more accurate, but is also two times faster than the state-of-the-art when running solely on the CPU. Running on the GPU, we show that our approach requires ~24 milliseconds to remove specular highlights in an image with 3840x2160 (4k) resolution. That makes our GPU implementation more than one order of magnitude (20x) faster than the state-of-the-art for 4k resolution images, while providing the desired effect accurately.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2018 > Real-Time High-Quality Specular...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Real-Time High-Quality Specular...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 24/08/2018 23:07 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPAW/3RMMGU8
zipped data URLhttp://urlib.net/zip/8JMKD3MGPAW/3RMMGU8
Languageen
Target FileSIBGRAPI 2018 - Main Track.pdf
User Groupmarciocfmacedo@hotmail.com
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPAW/3RPADUS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2018/09.03.20.37 10
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


Close