SpA-Former: Transformer image shadow detection and removal via spatial attention

SpA-Former: Transformer image shadow detection and removal via spatial attention

In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-10
Hauptverfasser: Xiao Feng Zhang, Chao Chen Gu, Zhu, Shan Ying
Format: Artikel
Sprache:eng
Schlagworte:
Fourier series
Fourier transforms
Shadows
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Xiao Feng Zhang
Chao Chen Gu
Zhu, Shan Ying
description In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpA-former is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/zhangbaijin/SpA-Former-shadow-removal
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2679947150</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2679947150</sourcerecordid><originalsourceid>FETCH-proquest_journals_26799471503</originalsourceid><addsrcrecordid>eNqNjsEKgkAURYcgSMp_eNBaGGc0s11E0jLIfTzyWSM6YzOj_X4WfUCrey_nLO6MBULKONomQixY6FzDORebTKSpDNj50u-jwtiO7A5Ki9rV3wGqwzuBe2BlXlCRp5tXRgPqCix1ZsQWRoXgevRq6ug96Y-xYvMaW0fhL5dsXRzLwynqrXkO5Py1MYPVE7pOJ_I8yeKUy_-sN2fBPzc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2679947150</pqid></control><display><type>article</type><title>SpA-Former: Transformer image shadow detection and removal via spatial attention</title><source>Free E- Journals</source><creator>Xiao Feng Zhang ; Chao Chen Gu ; Zhu, Shan Ying</creator><creatorcontrib>Xiao Feng Zhang ; Chao Chen Gu ; Zhu, Shan Ying</creatorcontrib><description>In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpA-former is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/zhangbaijin/SpA-Former-shadow-removal</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Fourier series ; Fourier transforms ; Shadows</subject><ispartof>arXiv.org, 2022-10</ispartof><rights>2022. 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.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Xiao Feng Zhang</creatorcontrib><creatorcontrib>Chao Chen Gu</creatorcontrib><creatorcontrib>Zhu, Shan Ying</creatorcontrib><title>SpA-Former: Transformer image shadow detection and removal via spatial attention</title><title>arXiv.org</title><description>In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpA-former is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/zhangbaijin/SpA-Former-shadow-removal</description><subject>Fourier series</subject><subject>Fourier transforms</subject><subject>Shadows</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjsEKgkAURYcgSMp_eNBaGGc0s11E0jLIfTzyWSM6YzOj_X4WfUCrey_nLO6MBULKONomQixY6FzDORebTKSpDNj50u-jwtiO7A5Ki9rV3wGqwzuBe2BlXlCRp5tXRgPqCix1ZsQWRoXgevRq6ug96Y-xYvMaW0fhL5dsXRzLwynqrXkO5Py1MYPVE7pOJ_I8yeKUy_-sN2fBPzc</recordid><startdate>20221017</startdate><enddate>20221017</enddate><creator>Xiao Feng Zhang</creator><creator>Chao Chen Gu</creator><creator>Zhu, Shan Ying</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20221017</creationdate><title>SpA-Former: Transformer image shadow detection and removal via spatial attention</title><author>Xiao Feng Zhang ; Chao Chen Gu ; Zhu, Shan Ying</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26799471503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Fourier series</topic><topic>Fourier transforms</topic><topic>Shadows</topic><toplevel>online_resources</toplevel><creatorcontrib>Xiao Feng Zhang</creatorcontrib><creatorcontrib>Chao Chen Gu</creatorcontrib><creatorcontrib>Zhu, Shan Ying</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xiao Feng Zhang</au><au>Chao Chen Gu</au><au>Zhu, Shan Ying</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>SpA-Former: Transformer image shadow detection and removal via spatial attention</atitle><jtitle>arXiv.org</jtitle><date>2022-10-17</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpA-former is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/zhangbaijin/SpA-Former-shadow-removal</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2679947150
source Free E- Journals
subjects Fourier series
Fourier transforms
Shadows
title SpA-Former: Transformer image shadow detection and removal via spatial attention
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T08%3A57%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=SpA-Former:%20Transformer%20image%20shadow%20detection%20and%20removal%20via%20spatial%20attention&rft.jtitle=arXiv.org&rft.au=Xiao%20Feng%20Zhang&rft.date=2022-10-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2679947150%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2679947150&rft_id=info:pmid/&rfr_iscdi=true