File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Lighting direction estimation of a shaded image by a surface-input regression network

TitleLighting direction estimation of a shaded image by a surface-input regression network
Authors
Issue Date2007
PublisherInstitute of Electrical and Electronics Engineers. The Journals web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500
Citation
The 2007 International Joint Conference on Neural Networks (IJCNN 2007), Orlando, FL., 12-17 August 2007. In IEEE International Conference on Neural Networks Proceedings, 2007, p. 201-206 How to Cite?
AbstractIn augmented reality (AR), the lighting direction plays an important role to the quality of the augmented scene. The corresponding lighting direction estimation is a challenging problem as it depends on an extra unknown variable - reflectance of the material. In this article, we propose to estimate the lighting direction by a neural network (NN) which is trained by a sample set. Since the empirical reflectance of a captured scene is in form of scattered points, we unify the representation of reflectance as a two dimensional polynomials. Moreover, a novel neural network model is presented to construct the mapping from reflectance to lighting direction. Contrary to the existing NNs, the proposed model accepts surface input pattern in which the drawbacks of feature vector are overcome. Experimental results of 2000 lighting estimations with unknown reflectances are presented to demonstrate the performance of the proposed algorithm. ©2007 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/196698
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorChow, CK-
dc.contributor.authorYuen, SY-
dc.date.accessioned2014-04-24T02:10:34Z-
dc.date.available2014-04-24T02:10:34Z-
dc.date.issued2007-
dc.identifier.citationThe 2007 International Joint Conference on Neural Networks (IJCNN 2007), Orlando, FL., 12-17 August 2007. In IEEE International Conference on Neural Networks Proceedings, 2007, p. 201-206-
dc.identifier.isbn978-1-4244-1379-9-
dc.identifier.issn1098-7576-
dc.identifier.urihttp://hdl.handle.net/10722/196698-
dc.description.abstractIn augmented reality (AR), the lighting direction plays an important role to the quality of the augmented scene. The corresponding lighting direction estimation is a challenging problem as it depends on an extra unknown variable - reflectance of the material. In this article, we propose to estimate the lighting direction by a neural network (NN) which is trained by a sample set. Since the empirical reflectance of a captured scene is in form of scattered points, we unify the representation of reflectance as a two dimensional polynomials. Moreover, a novel neural network model is presented to construct the mapping from reflectance to lighting direction. Contrary to the existing NNs, the proposed model accepts surface input pattern in which the drawbacks of feature vector are overcome. Experimental results of 2000 lighting estimations with unknown reflectances are presented to demonstrate the performance of the proposed algorithm. ©2007 IEEE.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journals web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500-
dc.relation.ispartofIEEE International Conference on Neural Networks Proceedings-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rightsIEEE International Conference on Neural Networks Proceedings. Copyright © Institute of Electrical and Electronics Engineers.-
dc.titleLighting direction estimation of a shaded image by a surface-input regression network-
dc.typeConference_Paper-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/IJCNN.2007.4370955-
dc.identifier.scopuseid_2-s2.0-51749118059-
dc.identifier.spage201-
dc.identifier.epage206-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 160603 amended-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats