Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes
Identifieur interne : 000126 ( UK/Analysis ); précédent : 000125; suivant : 000127Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes
Auteurs : David Elizondo [Royaume-Uni] ; Shang-Ming Zhou [Royaume-Uni] ; Charalambos Chrysostomou [Royaume-Uni]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2008.
English descriptors
Abstract
Abstract: This paper presents a novel neural network approach to recovering of 3D surfaces from single gray scale images. The proposed neural network uses photometric stereo to estimate local surfaces orientation for surfaces at each point of the surface that was observed from same viewpoint but with different illumination direction in surfaces that follow the Lambertian reflection model. The parameters for the neural network are a 3x3 brightness patch with pixel values of the image and the light source direction. The light source direction of the surface is calculated using two different approaches. The first approach uses a mathematical method and the second one a neural network method. The images used to test the neural network were both synthetic and real images. Only synthetic images were used to compare the approaches mainly because the surface was known and the error could be calculated. The results show that the proposed neural network is able to recover the surface with a highly accurately estimate.
Url:
DOI: 10.1007/978-3-540-87536-9_88
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001083
- to stream Istex, to step Curation: 000D86
- to stream Istex, to step Checkpoint: 000B70
- to stream Main, to step Merge: 001154
- to stream Main, to step Curation: 001141
- to stream Main, to step Exploration: 001141
- to stream UK, to step Extraction: 000126
Links to Exploration step
ISTEX:17CCF22342087C53718629ED4B1E69BD95412322Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes</title>
<author><name sortKey="Elizondo, David" sort="Elizondo, David" uniqKey="Elizondo D" first="David" last="Elizondo">David Elizondo</name>
</author>
<author><name sortKey="Zhou, Shang Ming" sort="Zhou, Shang Ming" uniqKey="Zhou S" first="Shang-Ming" last="Zhou">Shang-Ming Zhou</name>
</author>
<author><name sortKey="Chrysostomou, Charalambos" sort="Chrysostomou, Charalambos" uniqKey="Chrysostomou C" first="Charalambos" last="Chrysostomou">Charalambos Chrysostomou</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:17CCF22342087C53718629ED4B1E69BD95412322</idno>
<date when="2008" year="2008">2008</date>
<idno type="doi">10.1007/978-3-540-87536-9_88</idno>
<idno type="url">https://api.istex.fr/document/17CCF22342087C53718629ED4B1E69BD95412322/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">001083</idno>
<idno type="wicri:Area/Istex/Curation">000D86</idno>
<idno type="wicri:Area/Istex/Checkpoint">000B70</idno>
<idno type="wicri:doubleKey">0302-9743:2008:Elizondo D:surface:reconstruction:techniques</idno>
<idno type="wicri:Area/Main/Merge">001154</idno>
<idno type="wicri:Area/Main/Curation">001141</idno>
<idno type="wicri:Area/Main/Exploration">001141</idno>
<idno type="wicri:Area/UK/Extraction">000126</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes</title>
<author><name sortKey="Elizondo, David" sort="Elizondo, David" uniqKey="Elizondo D" first="David" last="Elizondo">David Elizondo</name>
<affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country>
<wicri:regionArea>Centre for Computational Intelligence, School of Computing, De Montfort University, LE1 9BH, The Gateway, Leicester</wicri:regionArea>
<wicri:noRegion>Leicester</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Royaume-Uni</country>
</affiliation>
</author>
<author><name sortKey="Zhou, Shang Ming" sort="Zhou, Shang Ming" uniqKey="Zhou S" first="Shang-Ming" last="Zhou">Shang-Ming Zhou</name>
<affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country>
<wicri:regionArea>Centre for Computational Intelligence, School of Computing, De Montfort University, LE1 9BH, The Gateway, Leicester</wicri:regionArea>
<wicri:noRegion>Leicester</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Royaume-Uni</country>
</affiliation>
</author>
<author><name sortKey="Chrysostomou, Charalambos" sort="Chrysostomou, Charalambos" uniqKey="Chrysostomou C" first="Charalambos" last="Chrysostomou">Charalambos Chrysostomou</name>
<affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country>
<wicri:regionArea>Centre for Computational Intelligence, School of Computing, De Montfort University, LE1 9BH, The Gateway, Leicester</wicri:regionArea>
<wicri:noRegion>Leicester</wicri:noRegion>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: charalambos_chrysostomou@hotmail.com</wicri:noCountry>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2008</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
</series>
<idno type="istex">17CCF22342087C53718629ED4B1E69BD95412322</idno>
<idno type="DOI">10.1007/978-3-540-87536-9_88</idno>
<idno type="ChapterID">Chap88</idno>
<idno type="ChapterID">88</idno>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>3D surfaces</term>
<term>Neural networks</term>
<term>light sources</term>
<term>noisy scenes</term>
<term>reconstruction</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: This paper presents a novel neural network approach to recovering of 3D surfaces from single gray scale images. The proposed neural network uses photometric stereo to estimate local surfaces orientation for surfaces at each point of the surface that was observed from same viewpoint but with different illumination direction in surfaces that follow the Lambertian reflection model. The parameters for the neural network are a 3x3 brightness patch with pixel values of the image and the light source direction. The light source direction of the surface is calculated using two different approaches. The first approach uses a mathematical method and the second one a neural network method. The images used to test the neural network were both synthetic and real images. Only synthetic images were used to compare the approaches mainly because the surface was known and the error could be calculated. The results show that the proposed neural network is able to recover the surface with a highly accurately estimate.</div>
</front>
</TEI>
<affiliations><list><country><li>Royaume-Uni</li>
</country>
</list>
<tree><country name="Royaume-Uni"><noRegion><name sortKey="Elizondo, David" sort="Elizondo, David" uniqKey="Elizondo D" first="David" last="Elizondo">David Elizondo</name>
</noRegion>
<name sortKey="Chrysostomou, Charalambos" sort="Chrysostomou, Charalambos" uniqKey="Chrysostomou C" first="Charalambos" last="Chrysostomou">Charalambos Chrysostomou</name>
<name sortKey="Elizondo, David" sort="Elizondo, David" uniqKey="Elizondo D" first="David" last="Elizondo">David Elizondo</name>
<name sortKey="Zhou, Shang Ming" sort="Zhou, Shang Ming" uniqKey="Zhou S" first="Shang-Ming" last="Zhou">Shang-Ming Zhou</name>
<name sortKey="Zhou, Shang Ming" sort="Zhou, Shang Ming" uniqKey="Zhou S" first="Shang-Ming" last="Zhou">Shang-Ming Zhou</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/MozartV1/Data/UK/Analysis
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000126 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/UK/Analysis/biblio.hfd -nk 000126 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Musique |area= MozartV1 |flux= UK |étape= Analysis |type= RBID |clé= ISTEX:17CCF22342087C53718629ED4B1E69BD95412322 |texte= Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes }}
This area was generated with Dilib version V0.6.20. |