NeRD: Neural field-based Demosaicking

NeRD: Neural field-based Demosaicking

We introduce NeRD, a new demosaicking method for generating full-color images from Bayer patterns. Our approach leverages advancements in neural fields to perform demosaicking by representing an image as a coordinate-based neural network with sine activation functions. The inputs to the network are...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-04
Hauptverfasser: Kerepecky, Tomas, Sroubek, Filip, Novozamsky, Adam, Flusser, Jan
Format: Artikel
Sprache:eng
Schlagworte:
Coders
Color imagery
Image quality
Trigonometric functions
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 Kerepecky, Tomas
Sroubek, Filip
Novozamsky, Adam
Flusser, Jan
description We introduce NeRD, a new demosaicking method for generating full-color images from Bayer patterns. Our approach leverages advancements in neural fields to perform demosaicking by representing an image as a coordinate-based neural network with sine activation functions. The inputs to the network are spatial coordinates and a low-resolution Bayer pattern, while the outputs are the corresponding RGB values. An encoder network, which is a blend of ResNet and U-net, enhances the implicit neural representation of the image to improve its quality and ensure spatial consistency through prior learning. Our experimental results demonstrate that NeRD outperforms traditional and state-of-the-art CNN-based methods and significantly closes the gap to transformer-based methods.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2801015058</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2801015058</sourcerecordid><originalsourceid>FETCH-proquest_journals_28010150583</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQ9UsNcrFS8EstLUrMUUjLTM1J0U1KLE5NUXBJzc0vTsxMzs7MS-dhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjCwNDA0NTA1MLY-JUAQClMy4u</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2801015058</pqid></control><display><type>article</type><title>NeRD: Neural field-based Demosaicking</title><source>Free E- Journals</source><creator>Kerepecky, Tomas ; Sroubek, Filip ; Novozamsky, Adam ; Flusser, Jan</creator><creatorcontrib>Kerepecky, Tomas ; Sroubek, Filip ; Novozamsky, Adam ; Flusser, Jan</creatorcontrib><description>We introduce NeRD, a new demosaicking method for generating full-color images from Bayer patterns. Our approach leverages advancements in neural fields to perform demosaicking by representing an image as a coordinate-based neural network with sine activation functions. The inputs to the network are spatial coordinates and a low-resolution Bayer pattern, while the outputs are the corresponding RGB values. An encoder network, which is a blend of ResNet and U-net, enhances the implicit neural representation of the image to improve its quality and ensure spatial consistency through prior learning. Our experimental results demonstrate that NeRD outperforms traditional and state-of-the-art CNN-based methods and significantly closes the gap to transformer-based methods.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Coders ; Color imagery ; Image quality ; Trigonometric functions</subject><ispartof>arXiv.org, 2023-04</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>Kerepecky, Tomas</creatorcontrib><creatorcontrib>Sroubek, Filip</creatorcontrib><creatorcontrib>Novozamsky, Adam</creatorcontrib><creatorcontrib>Flusser, Jan</creatorcontrib><title>NeRD: Neural field-based Demosaicking</title><title>arXiv.org</title><description>We introduce NeRD, a new demosaicking method for generating full-color images from Bayer patterns. Our approach leverages advancements in neural fields to perform demosaicking by representing an image as a coordinate-based neural network with sine activation functions. The inputs to the network are spatial coordinates and a low-resolution Bayer pattern, while the outputs are the corresponding RGB values. An encoder network, which is a blend of ResNet and U-net, enhances the implicit neural representation of the image to improve its quality and ensure spatial consistency through prior learning. Our experimental results demonstrate that NeRD outperforms traditional and state-of-the-art CNN-based methods and significantly closes the gap to transformer-based methods.</description><subject>Coders</subject><subject>Color imagery</subject><subject>Image quality</subject><subject>Trigonometric functions</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQ9UsNcrFS8EstLUrMUUjLTM1J0U1KLE5NUXBJzc0vTsxMzs7MS-dhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjCwNDA0NTA1MLY-JUAQClMy4u</recordid><startdate>20230413</startdate><enddate>20230413</enddate><creator>Kerepecky, Tomas</creator><creator>Sroubek, Filip</creator><creator>Novozamsky, Adam</creator><creator>Flusser, Jan</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>20230413</creationdate><title>NeRD: Neural field-based Demosaicking</title><author>Kerepecky, Tomas ; Sroubek, Filip ; Novozamsky, Adam ; Flusser, Jan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28010150583</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Coders</topic><topic>Color imagery</topic><topic>Image quality</topic><topic>Trigonometric functions</topic><toplevel>online_resources</toplevel><creatorcontrib>Kerepecky, Tomas</creatorcontrib><creatorcontrib>Sroubek, Filip</creatorcontrib><creatorcontrib>Novozamsky, Adam</creatorcontrib><creatorcontrib>Flusser, Jan</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>Access via ProQuest (Open Access)</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>Kerepecky, Tomas</au><au>Sroubek, Filip</au><au>Novozamsky, Adam</au><au>Flusser, Jan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>NeRD: Neural field-based Demosaicking</atitle><jtitle>arXiv.org</jtitle><date>2023-04-13</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>We introduce NeRD, a new demosaicking method for generating full-color images from Bayer patterns. Our approach leverages advancements in neural fields to perform demosaicking by representing an image as a coordinate-based neural network with sine activation functions. The inputs to the network are spatial coordinates and a low-resolution Bayer pattern, while the outputs are the corresponding RGB values. An encoder network, which is a blend of ResNet and U-net, enhances the implicit neural representation of the image to improve its quality and ensure spatial consistency through prior learning. Our experimental results demonstrate that NeRD outperforms traditional and state-of-the-art CNN-based methods and significantly closes the gap to transformer-based methods.</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, 2023-04
issn 2331-8422
language eng
recordid cdi_proquest_journals_2801015058
source Free E- Journals
subjects Coders
Color imagery
Image quality
Trigonometric functions
title NeRD: Neural field-based Demosaicking
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T04%3A30%3A42IST&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=NeRD:%20Neural%20field-based%20Demosaicking&rft.jtitle=arXiv.org&rft.au=Kerepecky,%20Tomas&rft.date=2023-04-13&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2801015058%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2801015058&rft_id=info:pmid/&rfr_iscdi=true