Benchmarking Single-Image Reflection Removal Algorithms
Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of...
Saved in:
| Published in | IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 1424 - 1441 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.02.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0162-8828 1939-3539 2160-9292 1939-3539 |
| DOI | 10.1109/TPAMI.2022.3168560 |
Cover
Loading…
| Abstract | Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR<inline-formula><tex-math notation="LaTeX">^{2+}</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mrow><mml:mn>2</mml:mn><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math><inline-graphic xlink:href="wan-ieq1-3168560.gif"/> </inline-formula> " with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/ . |
|---|---|
| AbstractList | Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR
" with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/. Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR<inline-formula><tex-math notation="LaTeX">^{2+}</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mrow><mml:mn>2</mml:mn><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math><inline-graphic xlink:href="wan-ieq1-3168560.gif"/> </inline-formula> " with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/ . Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR 2+ " with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/.Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR 2+ " with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/. Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset “SIR[Formula Omitted] ” with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/ . |
| Author | Duan, Ling-Yu Kot, Alex C. Shi, Boxin Wan, Renjie Li, Haoliang Hong, Yuchen |
| Author_xml | – sequence: 1 givenname: Renjie orcidid: 0000-0002-0161-0367 surname: Wan fullname: Wan, Renjie email: renjiewan@hkbu.edu.hk organization: Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China – sequence: 2 givenname: Boxin orcidid: 0000-0001-6749-0364 surname: Shi fullname: Shi, Boxin email: shiboxin@pku.edu.cn organization: National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China – sequence: 3 givenname: Haoliang orcidid: 0000-0002-8723-8112 surname: Li fullname: Li, Haoliang email: haoliali@cityu.edu.hk organization: Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China – sequence: 4 givenname: Yuchen orcidid: 0000-0003-2772-217X surname: Hong fullname: Hong, Yuchen email: yuchenhong.cn@gmail.com organization: National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China – sequence: 5 givenname: Ling-Yu orcidid: 0000-0002-4491-2023 surname: Duan fullname: Duan, Ling-Yu email: lingyu@pku.edu.cn organization: National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China – sequence: 6 givenname: Alex C. orcidid: 0000-0001-6262-8125 surname: Kot fullname: Kot, Alex C. email: eackot@ntu.edu.sg organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35439129$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kEtPAyEQx4nR2Pr4ApqYJl68bGVgF5ZjNT6aaDQ-zoTC0G7dhy5bE7-91FYPPXgYhsPvzwy_PbJdNzUScgR0CEDV-cvj6H48ZJSxIQeRZ4JukT4DQRPFFNsmfQqCJXnO8h7ZC2FOKaQZ5bukx7OUK2CqT-QF1nZWmfatqKeD53iUmIwrM8XBE_oSbVc0dbxWzacpB6Ny2rRFN6vCAdnxpgx4uO775PX66uXyNrl7uBlfju4SyzPoEkWdMEI5qxzSdAKIkFrunZlQAcplXlqZ5d6A914yOTEgjcM0U8rljirL98nZ6t33tvlYYOh0VQSLZWlqbBZBM5GxPBbwiJ5uoPNm0dZxO82kAC5T4CxSJ2tqManQ6fe2iL__0r9KIsBWgG2bEFr0fwhQvfSuf7zrpXe99h5D-UbIFp1ZuutaU5T_R49X0QIR_2YpKSiA5N8HSI7h |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TCSVT_2024_3405576 crossref_primary_10_1007_s11263_024_02240_2 crossref_primary_10_1049_ipr2_13165 crossref_primary_10_1109_ACCESS_2024_3474032 crossref_primary_10_1007_s11263_024_02073_z crossref_primary_10_1109_ACCESS_2024_3461782 crossref_primary_10_1109_TETCI_2024_3359063 crossref_primary_10_1109_TMM_2023_3330107 crossref_primary_10_1109_TPAMI_2023_3314972 crossref_primary_10_1109_TCSVT_2024_3471875 crossref_primary_10_1109_TPAMI_2023_3286429 crossref_primary_10_1109_TIP_2023_3347915 crossref_primary_10_1109_TMM_2023_3338413 crossref_primary_10_1109_TCE_2023_3303475 crossref_primary_10_52589_AJSTE_GWXJPEN4 crossref_primary_10_1109_LSP_2024_3456006 crossref_primary_10_1109_TIP_2023_3301332 crossref_primary_10_1109_TCSVT_2024_3403932 |
| Cites_doi | 10.1109/TPAMI.2013.45 10.1109/CVPR.2019.00837 10.1109/WACV48630.2021.00208 10.1109/CVPR42600.2020.01422 10.1109/CVPR42600.2020.00182 10.1109/CVPR.2018.00502 10.1145/1073204.1073269 10.1109/LSP.2014.2327071 10.1109/TPAMI.2007.1106 10.1109/ICIP.2015.7351139 10.7863/jum.1984.3.2.49 10.1109/ICCV.2017.351 10.1145/2964284.2967264 10.1109/CVPR.2014.281 10.1109/CVPR.2017.300 10.1007/978-3-540-24673-2_27 10.1109/ICCV48922.2021.00497 10.1109/CVPR.2019.00389 10.1109/ISCAS.2017.8050813 10.1109/TIP.2003.819861 10.1109/WACV.2009.5403036 10.1109/ISCAS.2013.6572002 10.1109/CVPR42600.2020.00362 10.1007/s11263-020-01372-5 10.1109/ICCV.2017.423 10.1109/CVPR.2008.4587768 10.1109/ICCV.2011.6126315 10.1145/2766940 10.1109/ICCV.1998.710848 10.1109/CVPR.2015.7298939 10.1109/TIP.2018.2849880 10.1109/ICIP.2016.7532311 10.1109/TIP.2018.2880510 10.1109/TIP.2006.881959 10.1109/CVPR42600.2020.00214 10.1109/CVPR.2017.618 10.1109/CVPR46437.2021.00767 10.1109/ACCESS.2019.2947266 10.1117/12.2320377 10.1016/j.jaad.2005.11.1082 10.1109/ICME.2017.8019527 10.1007/978-3-030-01261-8_6 10.1109/CVPR.2016.157 10.1109/CVPR.2018.00577 10.1007/978-3-319-54187-7_9 10.1109/TCI.2019.2899320 10.1109/CVPR42600.2020.00247 10.1109/CVPR.2017.190 10.1364/OE.18.024461 10.1109/CVPR46437.2021.01457 10.1109/TPAMI.2019.2921574 10.1109/CVPR.2006.106 10.1145/3510821 10.1007/s10489-022-04391-6 10.1007/978-3-319-10602-1_48 10.1109/ICCV.2005.216 10.1109/TPAMI.2011.87 10.1103/PhysRevLett.126.174301 10.1109/CVPR.2018.00503 10.1109/CVPR.2019.00256 10.1007/s11263-006-0029-5 10.1109/CVPR.2014.346 10.1109/ICIP.2005.1530235 10.1007/978-3-642-15567-3_27 10.1007/978-3-030-01219-9_40 10.1109/CVPR.1999.786949 10.1109/ICME.2019.00222 10.1109/CVPR46437.2021.01319 10.1109/CVPRW56347.2022.00343 10.1109/TCI.2018.2860465 10.1109/CVPR.2019.00165 10.1109/ICCV.2013.302 10.1007/s11263-019-01276-z 10.1111/j.1151-2916.1955.tb14581.x 10.1109/ICCV.2017.244 10.1007/978-3-642-57769-7 10.1109/MSP.2008.930649 10.1109/TIP.2018.2808768 10.1109/CVPR.2019.00833 10.1109/TIP.2007.915548 10.1109/CVPR.2018.00068 10.1109/TPAMI.2020.3020554 10.1109/TPAMI.1987.4767940 10.1117/12.2083105 10.1109/ICCV.1999.790305 10.1109/TIP.2019.2923559 10.1109/ICCV.2019.00253 10.1109/CVPR.2000.855826 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TPAMI.2022.3168560 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic Technology Research Database |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 1441 |
| ExternalDocumentID | 35439129 10_1109_TPAMI_2022_3168560 9760117 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: HKBU grantid: 11.41.4541.179390 – fundername: PKU-NTU Joint Research Institute – fundername: CityU New Research Initiatives/Infrastructure grantid: APRC 9610528 – fundername: National Natural Science Foundation of China grantid: 62136001; 62088102; 61872012 funderid: 10.13039/501100001809 |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 5VS 9M8 AAYOK ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM RIG RNI RZB VH1 XJT 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c351t-90d6a69dc9de04b1ee14c3fdab0619d5f7c758fa1fff727ba17ade4599d8d09c3 |
| IEDL.DBID | RIE |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Fri Jul 11 07:06:18 EDT 2025 Mon Jun 30 06:51:07 EDT 2025 Thu Apr 03 07:03:20 EDT 2025 Tue Jul 01 01:43:03 EDT 2025 Thu Apr 24 23:03:56 EDT 2025 Wed Aug 27 02:54:13 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c351t-90d6a69dc9de04b1ee14c3fdab0619d5f7c758fa1fff727ba17ade4599d8d09c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-0161-0367 0000-0002-4491-2023 0000-0002-8723-8112 0000-0001-6262-8125 0000-0001-6749-0364 0000-0003-2772-217X |
| PMID | 35439129 |
| PQID | 2761374132 |
| PQPubID | 85458 |
| PageCount | 18 |
| ParticipantIDs | pubmed_primary_35439129 crossref_primary_10_1109_TPAMI_2022_3168560 proquest_journals_2761374132 crossref_citationtrail_10_1109_TPAMI_2022_3168560 proquest_miscellaneous_2652865213 ieee_primary_9760117 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-02-01 |
| PublicationDateYYYYMMDD | 2023-02-01 |
| PublicationDate_xml | – month: 02 year: 2023 text: 2023-02-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2023 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref57 ref56 ref59 ref58 ref53 ref52 ref55 ref54 ref51 ref50 ref46 ref48 ref47 ref42 ref41 ref43 ref49 Wang (ref84) 2015 ref8 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref36 ref31 Lee (ref37) 2018 ref30 ref33 Simonyan (ref69) 2014 ref32 ref39 ref38 Fan (ref44) 2020 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Chi (ref68) 2018 ref28 ref27 ref29 ref13 ref12 ref15 ref14 ref97 ref96 ref11 ref10 ref98 ref17 ref16 ref19 ref18 ref93 ref92 ref95 ref94 ref91 ref90 ref89 ref86 ref85 ref88 ref87 ref82 ref81 Lyu (ref7) ref83 ref80 Fischer (ref74) 2015 ref79 ref78 ref75 ref77 ref76 ref2 ref1 ref71 ref70 ref73 ref72 Kim (ref45) 2019 ref67 ref64 ref63 ref66 ref65 ref60 ref62 ref61 |
| References_xml | – ident: ref89 doi: 10.1109/TPAMI.2013.45 – ident: ref14 doi: 10.1109/CVPR.2019.00837 – ident: ref47 doi: 10.1109/WACV48630.2021.00208 – ident: ref52 doi: 10.1109/CVPR42600.2020.01422 – ident: ref21 doi: 10.1109/CVPR42600.2020.00182 – ident: ref39 doi: 10.1109/CVPR.2018.00502 – ident: ref81 doi: 10.1145/1073204.1073269 – ident: ref55 doi: 10.1109/LSP.2014.2327071 – ident: ref9 doi: 10.1109/TPAMI.2007.1106 – ident: ref61 doi: 10.1109/ICIP.2015.7351139 – year: 2015 ident: ref74 article-title: FlowNet: Learning optical flow with convolutional networks – ident: ref29 doi: 10.7863/jum.1984.3.2.49 – ident: ref12 doi: 10.1109/ICCV.2017.351 – ident: ref56 doi: 10.1145/2964284.2967264 – ident: ref62 doi: 10.1109/CVPR.2014.281 – ident: ref40 doi: 10.1109/CVPR.2017.300 – ident: ref20 doi: 10.1007/978-3-540-24673-2_27 – ident: ref49 doi: 10.1109/ICCV48922.2021.00497 – ident: ref42 doi: 10.1109/CVPR.2019.00389 – ident: ref85 doi: 10.1109/ISCAS.2017.8050813 – ident: ref91 doi: 10.1109/TIP.2003.819861 – ident: ref31 doi: 10.1109/WACV.2009.5403036 – ident: ref54 doi: 10.1109/ISCAS.2013.6572002 – ident: ref19 doi: 10.1109/CVPR42600.2020.00362 – ident: ref2 doi: 10.1007/s11263-020-01372-5 – ident: ref17 doi: 10.1109/ICCV.2017.423 – year: 2014 ident: ref69 article-title: Very deep convolutional networks for large-scale image recognition – ident: ref76 doi: 10.1109/CVPR.2008.4587768 – ident: ref3 doi: 10.1109/ICCV.2011.6126315 – ident: ref16 doi: 10.1145/2766940 – ident: ref83 doi: 10.1109/ICCV.1998.710848 – ident: ref1 doi: 10.1109/CVPR.2015.7298939 – ident: ref64 doi: 10.1109/TIP.2018.2849880 – ident: ref11 doi: 10.1109/ICIP.2016.7532311 – ident: ref87 doi: 10.1109/TIP.2018.2880510 – start-page: 14 532 volume-title: Proc. 33rd Int. Conf. Neural Inf. Process. Syst. ident: ref7 article-title: Reflection separation using a pair of unpolarized and polarized images – ident: ref93 doi: 10.1109/TIP.2006.881959 – ident: ref97 doi: 10.1109/CVPR42600.2020.00214 – ident: ref59 doi: 10.1109/CVPR.2017.618 – ident: ref51 doi: 10.1109/CVPR46437.2021.00767 – ident: ref67 doi: 10.1109/ACCESS.2019.2947266 – ident: ref27 doi: 10.1117/12.2320377 – ident: ref25 doi: 10.1016/j.jaad.2005.11.1082 – ident: ref33 doi: 10.1109/ICME.2017.8019527 – ident: ref8 doi: 10.1007/978-3-030-01261-8_6 – year: 2019 ident: ref45 article-title: Single image reflection removal with physically-based rendering – ident: ref63 doi: 10.1109/CVPR.2016.157 – ident: ref94 doi: 10.1109/CVPR.2018.00577 – ident: ref36 doi: 10.1007/978-3-319-54187-7_9 – year: 2018 ident: ref68 article-title: Single image reflection removal using deep encoder-decoder network – ident: ref30 doi: 10.1109/TCI.2019.2899320 – ident: ref23 doi: 10.1109/CVPR42600.2020.00247 – ident: ref77 doi: 10.1109/TPAMI.2013.45 – ident: ref32 doi: 10.1109/CVPR.2017.190 – ident: ref28 doi: 10.1364/OE.18.024461 – ident: ref53 doi: 10.1109/CVPR46437.2021.01457 – ident: ref13 doi: 10.1109/TPAMI.2019.2921574 – ident: ref80 doi: 10.1109/CVPR.2006.106 – ident: ref46 doi: 10.1145/3510821 – ident: ref48 doi: 10.1007/s10489-022-04391-6 – ident: ref71 doi: 10.1007/978-3-319-10602-1_48 – ident: ref78 doi: 10.1109/ICCV.2005.216 – ident: ref60 doi: 10.1109/TPAMI.2011.87 – ident: ref96 doi: 10.1103/PhysRevLett.126.174301 – ident: ref15 doi: 10.1109/CVPR.2018.00503 – ident: ref66 doi: 10.1109/CVPR.2019.00256 – ident: ref4 doi: 10.1007/s11263-006-0029-5 – year: 2020 ident: ref44 article-title: Deep reflection prior – ident: ref10 doi: 10.1109/CVPR.2014.346 – year: 2015 ident: ref84 article-title: Automatic layer separation using light field imaging – ident: ref79 doi: 10.1109/ICIP.2005.1530235 – ident: ref98 doi: 10.1007/978-3-642-15567-3_27 – ident: ref70 doi: 10.1007/978-3-030-01219-9_40 – ident: ref5 doi: 10.1109/CVPR.1999.786949 – ident: ref43 doi: 10.1109/ICME.2019.00222 – ident: ref50 doi: 10.1109/CVPR46437.2021.01319 – ident: ref90 doi: 10.1109/CVPRW56347.2022.00343 – ident: ref86 doi: 10.1109/TCI.2018.2860465 – ident: ref65 doi: 10.1109/CVPR.2019.00165 – ident: ref57 doi: 10.1109/ICCV.2013.302 – ident: ref82 doi: 10.1007/s11263-019-01276-z – ident: ref22 doi: 10.1111/j.1151-2916.1955.tb14581.x – ident: ref38 doi: 10.1109/ICCV.2017.244 – ident: ref24 doi: 10.1007/978-3-642-57769-7 – ident: ref92 doi: 10.1109/MSP.2008.930649 – ident: ref34 doi: 10.1109/TIP.2018.2808768 – year: 2018 ident: ref37 article-title: Generative single image reflection separation – ident: ref75 doi: 10.1109/CVPR.1999.786949 – ident: ref35 doi: 10.1109/CVPR.2019.00833 – ident: ref72 doi: 10.1109/TIP.2007.915548 – ident: ref18 doi: 10.1109/CVPR.2018.00068 – ident: ref95 doi: 10.1109/TPAMI.2020.3020554 – ident: ref26 doi: 10.1109/TPAMI.1987.4767940 – ident: ref88 doi: 10.1117/12.2083105 – ident: ref6 doi: 10.1109/ICCV.1999.790305 – ident: ref58 doi: 10.1109/TIP.2019.2923559 – ident: ref41 doi: 10.1109/ICCV.2019.00253 – ident: ref73 doi: 10.1109/CVPR.2000.855826 |
| SSID | ssj0014503 |
| Score | 2.5226796 |
| Snippet | Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1424 |
| SubjectTerms | Algorithms benchmark dataset Benchmark testing Benchmarks Cameras Datasets Deep learning Glass Image quality Mathematical models Reflection Reflection removal Reflectivity State-of-the-art reviews Taxonomy |
| Title | Benchmarking Single-Image Reflection Removal Algorithms |
| URI | https://ieeexplore.ieee.org/document/9760117 https://www.ncbi.nlm.nih.gov/pubmed/35439129 https://www.proquest.com/docview/2761374132 https://www.proquest.com/docview/2652865213 |
| Volume | 45 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjR3LTtwwcAQcEByA8miXQhWk3kqWOHGS9ZEiECAtQi1I3CI_xlB1N0GQ5cDXM3YeVFWLuCRO4jiOPeOZ8bwAvlqtTJxnUagQRchNJEM1IsGVWykl0lKpvNf7-CI7vebnN-nNHOz3vjCI6I3PcOiKXpdvKj1zW2UHwhlwsHwe5klwa3y1eo0BT30WZOJgCMNJjOgcZCJxcHV5OD4jUTCOhy5NE9H4JVhMUudz6jnLV3rkE6z8n9f0NOdkFcZdbxtTk9_DWa2G-vmvQI7v_Z01WGmZz-CwgZYPMIflOqx2iR2CFs_XYfmPKIUbkH-nu3dT6XfVg590mGB4NqWFKPiBduJtuUoqTqsn1_jktnr4Vd9NHzfh-uT46ug0bPMthDpJWR2KyGQyE0YLgxFXDJFxnVgjFRF9YVKba5IurGTWWmJ7lGS5NMhTIczIREInW7BQViV-goCuRKyUdUpBLgWtZFyZEZ0RR1nEkwGwbtQL3QYjdzkxJoUXSiJR-Ekr3KQV7aQN4Fv_zn0TiuPN2htuxPua7WAPYKeb3KLF1seCgJUlxFol8QD2-seEZ055IkusZlQnS50Tb8yo7x8boOjb7mBp-9_f_AxLLkl9Y-u9Awv1wwx3iZWp1RcPwy-N3exG |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjR1dT9RAcIKYID6IAuIpakl4wx7ddtvePqKR3ClHiB4Jb81-zIrxriXQ88Ff7-z2A2PA-NJu2-12uzuzM7PzBbBvtTJxnkWhQhQhN5EM1YgEV26llEhLpfJe79PTbHzOP12kFyvwrveFQURvfIZDV_S6fFPppdsqOxTOgIPlD-Bh6pxxG2-tXmfAU58HmXgYwnESJDoXmUgczs6OphMSBuN46BI1EZVfh7UkdV6nnre8pUg-xcr93KanOscbMO362xib_BguazXUv_4K5fi_P_QUnrTsZ3DUwMszWMFyEza61A5Bi-mb8PiPOIVbkL-nu5cL6ffVg690mGM4WdBSFHxBO_fWXCUVF9VP1_j8W3X9vb5c3GzD-fHH2Ydx2GZcCHWSsjoUkclkJowWBiOuGCLjOrFGKiL7wqQ21yRfWMmstcT4KMlyaZCnQpiRiYROnsNqWZX4AgK6ErFS1qkFuRS0lnFlRnRGHGURTwbAulEvdBuO3GXFmBdeLIlE4SetcJNWtJM2gIP-nasmGMc_a2-5Ee9rtoM9gN1ucosWX28KAleWEHOVxAPY6x8Tpjn1iSyxWlKdLHVuvDGjvu80QNG33cHSy7u_-RYejWfTk-Jkcvr5Fay7lPWN5fcurNbXS3xNjE2t3nh4_g0It--O |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Benchmarking+Single-Image+Reflection+Removal+Algorithms&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Wan%2C+Renjie&rft.au=Shi%2C+Boxin&rft.au=Li%2C+Haoliang&rft.au=Hong%2C+Yuchen&rft.date=2023-02-01&rft.pub=IEEE&rft.issn=0162-8828&rft.volume=45&rft.issue=2&rft.spage=1424&rft.epage=1441&rft_id=info:doi/10.1109%2FTPAMI.2022.3168560&rft_id=info%3Apmid%2F35439129&rft.externalDocID=9760117 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |