Generalized Deep Image to Image Regression
We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery. Our proposed architecture: the Recursively Branched Deconvolutional Network (RBDN) develops a cheap multi-context image represe...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
10.12.2016
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery. Our proposed architecture: the Recursively Branched Deconvolutional Network (RBDN) develops a cheap multi-context image representation very early on using an efficient recursive branching scheme with extensive parameter sharing and learnable upsampling. This multi-context representation is subjected to a highly non-linear locality preserving transformation by the remainder of our network comprising of a series of convolutions/deconvolutions without any spatial downsampling. The RBDN architecture is fully convolutional and can handle variable sized images during inference. We provide qualitative/quantitative results on \(3\) diverse tasks: relighting, denoising and colorization and show that our proposed RBDN architecture obtains comparable results to the state-of-the-art on each of these tasks when used off-the-shelf without any post processing or task-specific architectural modifications. |
---|---|
AbstractList | We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery. Our proposed architecture: the Recursively Branched Deconvolutional Network (RBDN) develops a cheap multi-context image representation very early on using an efficient recursive branching scheme with extensive parameter sharing and learnable upsampling. This multi-context representation is subjected to a highly non-linear locality preserving transformation by the remainder of our network comprising of a series of convolutions/deconvolutions without any spatial downsampling. The RBDN architecture is fully convolutional and can handle variable sized images during inference. We provide qualitative/quantitative results on \(3\) diverse tasks: relighting, denoising and colorization and show that our proposed RBDN architecture obtains comparable results to the state-of-the-art on each of these tasks when used off-the-shelf without any post processing or task-specific architectural modifications. |
Author | Davis, Larry S Santhanam, Venkataraman Morariu, Vlad I |
Author_xml | – sequence: 1 givenname: Venkataraman surname: Santhanam fullname: Santhanam, Venkataraman – sequence: 2 givenname: Vlad surname: Morariu middlename: I fullname: Morariu, Vlad I – sequence: 3 givenname: Larry surname: Davis middlename: S fullname: Davis, Larry S |
BookMark | eNrjYmDJy89LZWLgNDI2NtS1MDEy4mDgLS7OMjAwMDIzNzI1NeZk0HJPzUstSszJrEpNUXBJTS1Q8MxNTE9VKMmHMoJS04tSi4sz8_N4GFjTEnOKU3mhNDeDsptriLOHbkFRfmFpanFJfFZ-aVEeUCreyMDCwMTUFGiPMXGqAPeyMfM |
ContentType | Paper |
Copyright | 2016. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2016. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection ProQuest Engineering Database Publicly Available Content (ProQuest) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_20804550023 |
IEDL.DBID | BENPR |
IngestDate | Tue Sep 24 23:15:37 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_20804550023 |
OpenAccessLink | https://www.proquest.com/docview/2080455002/abstract/?pq-origsite=%requestingapplication% |
PQID | 2080455002 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2080455002 |
PublicationCentury | 2000 |
PublicationDate | 20161210 |
PublicationDateYYYYMMDD | 2016-12-10 |
PublicationDate_xml | – month: 12 year: 2016 text: 20161210 day: 10 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2016 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.0601707 |
SecondaryResourceType | preprint |
Snippet | We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Artificial neural networks Neural networks Noise reduction Representations |
Title | Generalized Deep Image to Image Regression |
URI | https://www.proquest.com/docview/2080455002/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMTUzN0ixTEnVTQZ2vXRN0gwSgVnKzFTXICnNAhjdoDOmwAtk_cw8Qk28IkwjmBg8YHthQMsqYWUiuKBOyU8GjZEDO-kWBqAduAZG-olJoFGA5BJ9-4JCXdD9UaB5VuhlGswMrEaGJqAJW1YnV7-AIPh4i5GZObD1bIxR5ILrETdBBtaAxILUIiEGptQ8YQZ28PLL5GIRBi3o6c-ZVakpCi6pqQUKnrnAjK5Qkg9lBKWmQxas5okyKLu5hjh76MIsiIcmh-J4hOONxRhYgP36VAkGBWARZQy6-tnEOM3UJNU42TItJSXJMiXJ3DTJ2DTF0EySQQafSVL4paUZuIB1O_iOHUMDGQaWkqLSVFlg_VmSJMfAbOHmLgcNICDPt84VACMXeMk |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMTUzN0ixTEnVTQZ2vXRN0gwSgVnKzFTXICnNAhjdoDOmwAtk_cw8Qk28IkwjoANuxdBllbAyEVxQp-Qng8bIgZ10CwPQDlwDI_uCQl3QrVGg2VXoFRrMDKwmxsCqE7RT3M0dPsZiZGYObDEbYxSz4LrDTZCBNSCxILVIiIEpNU-YgR285DK5WIRBC3ric2ZVaoqCS2pqgYJnLjBzK5TkQxlBqemQRap5ogzKbq4hzh66MAvioUmgOB7hYGMxBhZgXz5VgkEBWCwZg657NjFOMzVJNU62TEtJSbJMSTI3TTI2TTE0k2SQwWeSFH5peQZOjxBfn3gfTz9vaQYuYN0OvmPH0ECGgaWkqDRVFlh_liTJgQMJAE6gdH8 |
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=Generalized+Deep+Image+to+Image+Regression&rft.jtitle=arXiv.org&rft.au=Santhanam%2C+Venkataraman&rft.au=Morariu%2C+Vlad+I&rft.au=Davis%2C+Larry+S&rft.date=2016-12-10&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |