Image Restoration with Deep Generative Models
Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which enforces some local image consistency in the recovered image. How tightly the prior assumptions are fulfilled has a big impact on the result...
Saved in:
Published in | 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6772 - 6776 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.04.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which enforces some local image consistency in the recovered image. How tightly the prior assumptions are fulfilled has a big impact on the resulting task performance. To obtain more flexibility, in this work, we proposed to design the image prior in a data-driven manner. Instead of explicitly defining the prior, we learn it using deep generative models. We demonstrate that this learned prior can be applied to many image restoration problems using an unified framework. |
---|---|
AbstractList | Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which enforces some local image consistency in the recovered image. How tightly the prior assumptions are fulfilled has a big impact on the resulting task performance. To obtain more flexibility, in this work, we proposed to design the image prior in a data-driven manner. Instead of explicitly defining the prior, we learn it using deep generative models. We demonstrate that this learned prior can be applied to many image restoration problems using an unified framework. |
Author | Hasegawa-Johnson, Mark Do, Minh N. Schwing, Alexander G. Chen, Chen Yeh, Raymond A. Lim, Teck Yian |
Author_xml | – sequence: 1 givenname: Raymond A. surname: Yeh fullname: Yeh, Raymond A. email: yeh17@illinois.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana Champaign, Champaign, IL, USA – sequence: 2 givenname: Teck Yian surname: Lim fullname: Lim, Teck Yian email: tlim11@illinois.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana Champaign, Champaign, IL, USA – sequence: 3 givenname: Chen surname: Chen fullname: Chen, Chen email: cchen156@illinois.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana Champaign, Champaign, IL, USA – sequence: 4 givenname: Alexander G. surname: Schwing fullname: Schwing, Alexander G. email: aschwing@illinois.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana Champaign, Champaign, IL, USA – sequence: 5 givenname: Mark surname: Hasegawa-Johnson fullname: Hasegawa-Johnson, Mark email: jhasegaw@illinois.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana Champaign, Champaign, IL, USA – sequence: 6 givenname: Minh N. surname: Do fullname: Do, Minh N. email: minhdo@illinois.edu organization: Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana Champaign, Champaign, IL, USA |
BookMark | eNotj81KAzEUhaMo2NZ5gm7yAhlv_pOlVK2FFsUquCvJzI2OtDNlMih9eyt2deB8cPjOmFy0XYuETDmUnIO_Wcxu1-vnUgB3pVNGSG7PSOGt41o6o4x27pyMhLSecQ_vV6TI-QsAhHHKajMibLELH0hfMA9dH4ama-lPM3zSO8Q9nWOLf-U30lVX4zZfk8sUthmLU07I28P96-yRLZ_mR5Ulq4TQA6u44gmStsFE0AaNgDqid7r2MYbae-Eh8SPxEhzIlGSKEIPVIlpRqUpOyPR_t0HEzb5vdqE_bE4H5S-fbUVK |
CitedBy_id | crossref_primary_10_15407_jai2022_01_288 |
ContentType | Conference Proceeding |
DBID | 6IE 6IH CBEJK RIE RIO |
DOI | 10.1109/ICASSP.2018.8462317 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library Online IEEE Proceedings Order Plans (POP) 1998-present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISBN | 9781538646588 1538646587 |
EISSN | 2379-190X |
EndPage | 6776 |
ExternalDocumentID | 8462317 |
Genre | orig-research |
GroupedDBID | 23M 29P 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI JC5 M43 OCL RIE RIL RIO RNS |
ID | FETCH-LOGICAL-c225t-c141f0f57a6b056e620dbe985d9bbad99290f1056930803ff3fb0ba752b72c4c3 |
IEDL.DBID | RIE |
IngestDate | Wed Jun 26 19:27:55 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c225t-c141f0f57a6b056e620dbe985d9bbad99290f1056930803ff3fb0ba752b72c4c3 |
PageCount | 5 |
ParticipantIDs | ieee_primary_8462317 |
PublicationCentury | 2000 |
PublicationDate | 2018-April |
PublicationDateYYYYMMDD | 2018-04-01 |
PublicationDate_xml | – month: 04 year: 2018 text: 2018-April |
PublicationDecade | 2010 |
PublicationTitle | 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
PublicationTitleAbbrev | ICASSP |
PublicationYear | 2018 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0002684756 ssj0008748 |
Score | 2.284824 |
Snippet | Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 6772 |
SubjectTerms | deep generative models Gallium nitride generative adversarial networks Generators Image resolution Image restoration Noise reduction Quantization (signal) Task analysis |
Title | Image Restoration with Deep Generative Models |
URI | https://ieeexplore.ieee.org/document/8462317 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED61nWDh0SLeysCIUydxYmdEhapFKqoolbpVtnNegLYq6cKvx3ZCeYiBLcoQ-ZX7Pp3vvg_gKpL2ECBHkopCE2aYJLmrBHB0Nk1Yguh7YUYP2WDK7mfprAHX214YRPTFZxi6R3-XXyz1xqXKuhYrLR3hTWgKGle9Wtt8ilMt8UrmdRQWnIlaZSiieXfYu5lMxq6US4T1Z374qXg46e_B6HMgVRXJc7gpVajff2k0_nek-9D5atwLxltIOoAGLg5h95vmYBvI8NWGkODRO8r4bQlcLja4RVwFlQi1i4CBM0l7eevAtH_31BuQ2jOBaPtnlkRHLDLUpFxmynIbzGJaKMxFWuRKySK3bIgay6mcA6KgiTGJUVRJnsaKx5rp5Ahai-UCjyFw3uMW_rWMUsVQClUwk_Es41KiBf3iBNpu4vNVJYsxr-d8-vfrM9hxi18VvZxDq1xv8MLieaku_UZ-AAUsnOQ |
link.rule.ids | 310,311,786,790,795,796,802,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwED2VMgALHy3iGw-MJE0aO05GVKhaaKuKtlK3ynbOC9BWkC78emwnlA8xsEUZIlvn3Hs6370HcBUKcwiQo8eSTHlUU-GlthPA0lkW0QjRzcL0B3FnQu-nbFqB6_UsDCK65jP07aO7y88WamVLZQ2DlYaO8A3YNDgf8GJaa11RsbolTsu8zMMJp0mpMxQGaaPbuhmNhraZK_HLD_1wVHGA0t6F_udSij6SJ3-VS1-9_1Jp_O9a96D-NbpHhmtQ2ocKzg9g55vqYA287otJIuTRecq4wBBbjSW3iEtSyFDbHEisTdrzWx0m7btxq-OVrgmeMv9m7qmQhjrQjItYGnaDcTPIJKYJy1IpRZYaPhRow6qsB2ISRFpHWgZScNaUvKmoig6hOl_M8QiIdR83BECJkEmKIpEZ1TGPYy4EGtjPjqFmNz5bFsIYs3LPJ3-_voStzrjfm_W6g4dT2LaBKFpgzqCav67w3KB7Li9cUD8AfnGgOA |
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%3Abook&rft.genre=proceeding&rft.title=2018+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29&rft.atitle=Image+Restoration+with+Deep+Generative+Models&rft.au=Yeh%2C+Raymond+A.&rft.au=Lim%2C+Teck+Yian&rft.au=Chen%2C+Chen&rft.au=Schwing%2C+Alexander+G.&rft.date=2018-04-01&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=6772&rft.epage=6776&rft_id=info:doi/10.1109%2FICASSP.2018.8462317&rft.externalDocID=8462317 |