Loading…
Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 1659 |
| container_issue | |
| container_start_page | 1643 |
| container_title | |
| container_volume | |
| creator | Conde, Marcos V. Kolmet, Manuel Seizinger, Tim Bishop, Tom E. Timofte, Radu Kong, Xiangyu Zhang, Dafeng Wu, Jinlong Wang, Fan Peng, Juewen Pan, Zhiyu Liu, Chengxin Luo, Xianrui Sun, Huiqiang Shen, Liao Cao, Zhiguo Xian, Ke Liu, Chaowei Chen, Zigeng Yang, Xingyi Liu, Songhua Jing, Yongcheng Mi, Michael Bi Wang, Xinchao Yang, Zhihao Lian, Wenyi Lai, Siyuan Zhang, Haichuan Hoang, Trung Yazdani, Amirsaeed Monga, Vishal Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjolund, Jens Schon, Thomas B. Zhao, Yuxuan Chen, Baoliang Xu, Yiqing JiXiangNiu |
| description | We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical properties.The aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens setups.To the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation. |
| doi_str_mv | 10.1109/CVPRW59228.2023.00166 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10208960</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10208960</ieee_id><sourcerecordid>10208960</sourcerecordid><originalsourceid>FETCH-LOGICAL-i1562-374df04e57f31976078e190eca891ce5d388de0da39c649b9e0ae401362b290a3</originalsourceid><addsrcrecordid>eNotjctKw0AUQEdBsNT8gcL8wMQ7M5nHXWqItlBUQtRlmSZ3bDRNSpKNf69FV2dzOIexGwmplIC3-dtL-W5QKZ8qUDoFkNaesQQdem1Ag8pQn7OFkhaEM9JesmSaPuHXA28M6gUrNtRPYh7Eifx--KI9L2KkeubVGPopDuMhzO3Qp_ypWpcFP414vg9dR_0H8ZKOwzhfsYsYuomSfy7Z60NR5SuxeX5c53cb0UpjldAuayJkZFzUEp0F50kiUB08yppMo71vCJqgsbYZ7pAgUAZSW7VTCEEv2fVftyWi7XFsD2H83kpQ4NGC_gEPs0pr</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report</title><source>IEEE Xplore All Conference Series</source><creator>Conde, Marcos V. ; Kolmet, Manuel ; Seizinger, Tim ; Bishop, Tom E. ; Timofte, Radu ; Kong, Xiangyu ; Zhang, Dafeng ; Wu, Jinlong ; Wang, Fan ; Peng, Juewen ; Pan, Zhiyu ; Liu, Chengxin ; Luo, Xianrui ; Sun, Huiqiang ; Shen, Liao ; Cao, Zhiguo ; Xian, Ke ; Liu, Chaowei ; Chen, Zigeng ; Yang, Xingyi ; Liu, Songhua ; Jing, Yongcheng ; Mi, Michael Bi ; Wang, Xinchao ; Yang, Zhihao ; Lian, Wenyi ; Lai, Siyuan ; Zhang, Haichuan ; Hoang, Trung ; Yazdani, Amirsaeed ; Monga, Vishal ; Luo, Ziwei ; Gustafsson, Fredrik K. ; Zhao, Zheng ; Sjolund, Jens ; Schon, Thomas B. ; Zhao, Yuxuan ; Chen, Baoliang ; Xu, Yiqing ; JiXiangNiu</creator><creatorcontrib>Conde, Marcos V. ; Kolmet, Manuel ; Seizinger, Tim ; Bishop, Tom E. ; Timofte, Radu ; Kong, Xiangyu ; Zhang, Dafeng ; Wu, Jinlong ; Wang, Fan ; Peng, Juewen ; Pan, Zhiyu ; Liu, Chengxin ; Luo, Xianrui ; Sun, Huiqiang ; Shen, Liao ; Cao, Zhiguo ; Xian, Ke ; Liu, Chaowei ; Chen, Zigeng ; Yang, Xingyi ; Liu, Songhua ; Jing, Yongcheng ; Mi, Michael Bi ; Wang, Xinchao ; Yang, Zhihao ; Lian, Wenyi ; Lai, Siyuan ; Zhang, Haichuan ; Hoang, Trung ; Yazdani, Amirsaeed ; Monga, Vishal ; Luo, Ziwei ; Gustafsson, Fredrik K. ; Zhao, Zheng ; Sjolund, Jens ; Schon, Thomas B. ; Zhao, Yuxuan ; Chen, Baoliang ; Xu, Yiqing ; JiXiangNiu</creatorcontrib><description>We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical properties.The aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens setups.To the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation.</description><identifier>EISSN: 2160-7516</identifier><identifier>EISBN: 9798350302493</identifier><identifier>DOI: 10.1109/CVPRW59228.2023.00166</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Benchmark testing ; Neural networks ; Photography ; Rendering (computer graphics) ; Training ; Transforms ; Visualization</subject><ispartof>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, p.1643-1659</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10208960$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,786,790,795,796,27958,54906,55283</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10208960$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Conde, Marcos V.</creatorcontrib><creatorcontrib>Kolmet, Manuel</creatorcontrib><creatorcontrib>Seizinger, Tim</creatorcontrib><creatorcontrib>Bishop, Tom E.</creatorcontrib><creatorcontrib>Timofte, Radu</creatorcontrib><creatorcontrib>Kong, Xiangyu</creatorcontrib><creatorcontrib>Zhang, Dafeng</creatorcontrib><creatorcontrib>Wu, Jinlong</creatorcontrib><creatorcontrib>Wang, Fan</creatorcontrib><creatorcontrib>Peng, Juewen</creatorcontrib><creatorcontrib>Pan, Zhiyu</creatorcontrib><creatorcontrib>Liu, Chengxin</creatorcontrib><creatorcontrib>Luo, Xianrui</creatorcontrib><creatorcontrib>Sun, Huiqiang</creatorcontrib><creatorcontrib>Shen, Liao</creatorcontrib><creatorcontrib>Cao, Zhiguo</creatorcontrib><creatorcontrib>Xian, Ke</creatorcontrib><creatorcontrib>Liu, Chaowei</creatorcontrib><creatorcontrib>Chen, Zigeng</creatorcontrib><creatorcontrib>Yang, Xingyi</creatorcontrib><creatorcontrib>Liu, Songhua</creatorcontrib><creatorcontrib>Jing, Yongcheng</creatorcontrib><creatorcontrib>Mi, Michael Bi</creatorcontrib><creatorcontrib>Wang, Xinchao</creatorcontrib><creatorcontrib>Yang, Zhihao</creatorcontrib><creatorcontrib>Lian, Wenyi</creatorcontrib><creatorcontrib>Lai, Siyuan</creatorcontrib><creatorcontrib>Zhang, Haichuan</creatorcontrib><creatorcontrib>Hoang, Trung</creatorcontrib><creatorcontrib>Yazdani, Amirsaeed</creatorcontrib><creatorcontrib>Monga, Vishal</creatorcontrib><creatorcontrib>Luo, Ziwei</creatorcontrib><creatorcontrib>Gustafsson, Fredrik K.</creatorcontrib><creatorcontrib>Zhao, Zheng</creatorcontrib><creatorcontrib>Sjolund, Jens</creatorcontrib><creatorcontrib>Schon, Thomas B.</creatorcontrib><creatorcontrib>Zhao, Yuxuan</creatorcontrib><creatorcontrib>Chen, Baoliang</creatorcontrib><creatorcontrib>Xu, Yiqing</creatorcontrib><creatorcontrib>JiXiangNiu</creatorcontrib><title>Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report</title><title>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</title><addtitle>CVPRW</addtitle><description>We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical properties.The aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens setups.To the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation.</description><subject>Benchmark testing</subject><subject>Neural networks</subject><subject>Photography</subject><subject>Rendering (computer graphics)</subject><subject>Training</subject><subject>Transforms</subject><subject>Visualization</subject><issn>2160-7516</issn><isbn>9798350302493</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjctKw0AUQEdBsNT8gcL8wMQ7M5nHXWqItlBUQtRlmSZ3bDRNSpKNf69FV2dzOIexGwmplIC3-dtL-W5QKZ8qUDoFkNaesQQdem1Ag8pQn7OFkhaEM9JesmSaPuHXA28M6gUrNtRPYh7Eifx--KI9L2KkeubVGPopDuMhzO3Qp_ypWpcFP414vg9dR_0H8ZKOwzhfsYsYuomSfy7Z60NR5SuxeX5c53cb0UpjldAuayJkZFzUEp0F50kiUB08yppMo71vCJqgsbYZ7pAgUAZSW7VTCEEv2fVftyWi7XFsD2H83kpQ4NGC_gEPs0pr</recordid><startdate>202306</startdate><enddate>202306</enddate><creator>Conde, Marcos V.</creator><creator>Kolmet, Manuel</creator><creator>Seizinger, Tim</creator><creator>Bishop, Tom E.</creator><creator>Timofte, Radu</creator><creator>Kong, Xiangyu</creator><creator>Zhang, Dafeng</creator><creator>Wu, Jinlong</creator><creator>Wang, Fan</creator><creator>Peng, Juewen</creator><creator>Pan, Zhiyu</creator><creator>Liu, Chengxin</creator><creator>Luo, Xianrui</creator><creator>Sun, Huiqiang</creator><creator>Shen, Liao</creator><creator>Cao, Zhiguo</creator><creator>Xian, Ke</creator><creator>Liu, Chaowei</creator><creator>Chen, Zigeng</creator><creator>Yang, Xingyi</creator><creator>Liu, Songhua</creator><creator>Jing, Yongcheng</creator><creator>Mi, Michael Bi</creator><creator>Wang, Xinchao</creator><creator>Yang, Zhihao</creator><creator>Lian, Wenyi</creator><creator>Lai, Siyuan</creator><creator>Zhang, Haichuan</creator><creator>Hoang, Trung</creator><creator>Yazdani, Amirsaeed</creator><creator>Monga, Vishal</creator><creator>Luo, Ziwei</creator><creator>Gustafsson, Fredrik K.</creator><creator>Zhao, Zheng</creator><creator>Sjolund, Jens</creator><creator>Schon, Thomas B.</creator><creator>Zhao, Yuxuan</creator><creator>Chen, Baoliang</creator><creator>Xu, Yiqing</creator><creator>JiXiangNiu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>202306</creationdate><title>Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report</title><author>Conde, Marcos V. ; Kolmet, Manuel ; Seizinger, Tim ; Bishop, Tom E. ; Timofte, Radu ; Kong, Xiangyu ; Zhang, Dafeng ; Wu, Jinlong ; Wang, Fan ; Peng, Juewen ; Pan, Zhiyu ; Liu, Chengxin ; Luo, Xianrui ; Sun, Huiqiang ; Shen, Liao ; Cao, Zhiguo ; Xian, Ke ; Liu, Chaowei ; Chen, Zigeng ; Yang, Xingyi ; Liu, Songhua ; Jing, Yongcheng ; Mi, Michael Bi ; Wang, Xinchao ; Yang, Zhihao ; Lian, Wenyi ; Lai, Siyuan ; Zhang, Haichuan ; Hoang, Trung ; Yazdani, Amirsaeed ; Monga, Vishal ; Luo, Ziwei ; Gustafsson, Fredrik K. ; Zhao, Zheng ; Sjolund, Jens ; Schon, Thomas B. ; Zhao, Yuxuan ; Chen, Baoliang ; Xu, Yiqing ; JiXiangNiu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i1562-374df04e57f31976078e190eca891ce5d388de0da39c649b9e0ae401362b290a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Benchmark testing</topic><topic>Neural networks</topic><topic>Photography</topic><topic>Rendering (computer graphics)</topic><topic>Training</topic><topic>Transforms</topic><topic>Visualization</topic><toplevel>online_resources</toplevel><creatorcontrib>Conde, Marcos V.</creatorcontrib><creatorcontrib>Kolmet, Manuel</creatorcontrib><creatorcontrib>Seizinger, Tim</creatorcontrib><creatorcontrib>Bishop, Tom E.</creatorcontrib><creatorcontrib>Timofte, Radu</creatorcontrib><creatorcontrib>Kong, Xiangyu</creatorcontrib><creatorcontrib>Zhang, Dafeng</creatorcontrib><creatorcontrib>Wu, Jinlong</creatorcontrib><creatorcontrib>Wang, Fan</creatorcontrib><creatorcontrib>Peng, Juewen</creatorcontrib><creatorcontrib>Pan, Zhiyu</creatorcontrib><creatorcontrib>Liu, Chengxin</creatorcontrib><creatorcontrib>Luo, Xianrui</creatorcontrib><creatorcontrib>Sun, Huiqiang</creatorcontrib><creatorcontrib>Shen, Liao</creatorcontrib><creatorcontrib>Cao, Zhiguo</creatorcontrib><creatorcontrib>Xian, Ke</creatorcontrib><creatorcontrib>Liu, Chaowei</creatorcontrib><creatorcontrib>Chen, Zigeng</creatorcontrib><creatorcontrib>Yang, Xingyi</creatorcontrib><creatorcontrib>Liu, Songhua</creatorcontrib><creatorcontrib>Jing, Yongcheng</creatorcontrib><creatorcontrib>Mi, Michael Bi</creatorcontrib><creatorcontrib>Wang, Xinchao</creatorcontrib><creatorcontrib>Yang, Zhihao</creatorcontrib><creatorcontrib>Lian, Wenyi</creatorcontrib><creatorcontrib>Lai, Siyuan</creatorcontrib><creatorcontrib>Zhang, Haichuan</creatorcontrib><creatorcontrib>Hoang, Trung</creatorcontrib><creatorcontrib>Yazdani, Amirsaeed</creatorcontrib><creatorcontrib>Monga, Vishal</creatorcontrib><creatorcontrib>Luo, Ziwei</creatorcontrib><creatorcontrib>Gustafsson, Fredrik K.</creatorcontrib><creatorcontrib>Zhao, Zheng</creatorcontrib><creatorcontrib>Sjolund, Jens</creatorcontrib><creatorcontrib>Schon, Thomas B.</creatorcontrib><creatorcontrib>Zhao, Yuxuan</creatorcontrib><creatorcontrib>Chen, Baoliang</creatorcontrib><creatorcontrib>Xu, Yiqing</creatorcontrib><creatorcontrib>JiXiangNiu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Conde, Marcos V.</au><au>Kolmet, Manuel</au><au>Seizinger, Tim</au><au>Bishop, Tom E.</au><au>Timofte, Radu</au><au>Kong, Xiangyu</au><au>Zhang, Dafeng</au><au>Wu, Jinlong</au><au>Wang, Fan</au><au>Peng, Juewen</au><au>Pan, Zhiyu</au><au>Liu, Chengxin</au><au>Luo, Xianrui</au><au>Sun, Huiqiang</au><au>Shen, Liao</au><au>Cao, Zhiguo</au><au>Xian, Ke</au><au>Liu, Chaowei</au><au>Chen, Zigeng</au><au>Yang, Xingyi</au><au>Liu, Songhua</au><au>Jing, Yongcheng</au><au>Mi, Michael Bi</au><au>Wang, Xinchao</au><au>Yang, Zhihao</au><au>Lian, Wenyi</au><au>Lai, Siyuan</au><au>Zhang, Haichuan</au><au>Hoang, Trung</au><au>Yazdani, Amirsaeed</au><au>Monga, Vishal</au><au>Luo, Ziwei</au><au>Gustafsson, Fredrik K.</au><au>Zhao, Zheng</au><au>Sjolund, Jens</au><au>Schon, Thomas B.</au><au>Zhao, Yuxuan</au><au>Chen, Baoliang</au><au>Xu, Yiqing</au><au>JiXiangNiu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report</atitle><btitle>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</btitle><stitle>CVPRW</stitle><date>2023-06</date><risdate>2023</risdate><spage>1643</spage><epage>1659</epage><pages>1643-1659</pages><eissn>2160-7516</eissn><eisbn>9798350302493</eisbn><coden>IEEPAD</coden><abstract>We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical properties.The aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens setups.To the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation.</abstract><pub>IEEE</pub><doi>10.1109/CVPRW59228.2023.00166</doi><tpages>17</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2160-7516 |
| ispartof | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, p.1643-1659 |
| issn | 2160-7516 |
| language | eng |
| recordid | cdi_ieee_primary_10208960 |
| source | IEEE Xplore All Conference Series |
| subjects | Benchmark testing Neural networks Photography Rendering (computer graphics) Training Transforms Visualization |
| title | Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T23%3A28%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Lens-to-Lens%20Bokeh%20Effect%20Transformation.%20NTIRE%202023%20Challenge%20Report&rft.btitle=2023%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20(CVPRW)&rft.au=Conde,%20Marcos%20V.&rft.date=2023-06&rft.spage=1643&rft.epage=1659&rft.pages=1643-1659&rft.eissn=2160-7516&rft.coden=IEEPAD&rft_id=info:doi/10.1109/CVPRW59228.2023.00166&rft.eisbn=9798350302493&rft_dat=%3Cieee_CHZPO%3E10208960%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i1562-374df04e57f31976078e190eca891ce5d388de0da39c649b9e0ae401362b290a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10208960&rfr_iscdi=true |