File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/IJCNN.2007.4370955
- Scopus: eid_2-s2.0-51749118059
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Lighting direction estimation of a shaded image by a surface-input regression network
Title | Lighting direction estimation of a shaded image by a surface-input regression network |
---|---|
Authors | |
Issue Date | 2007 |
Publisher | Institute 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? |
Abstract | In 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 Identifier | http://hdl.handle.net/10722/196698 |
ISBN | |
ISSN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chow, CK | - |
dc.contributor.author | Yuen, SY | - |
dc.date.accessioned | 2014-04-24T02:10:34Z | - |
dc.date.available | 2014-04-24T02:10:34Z | - |
dc.date.issued | 2007 | - |
dc.identifier.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 | - |
dc.identifier.isbn | 978-1-4244-1379-9 | - |
dc.identifier.issn | 1098-7576 | - |
dc.identifier.uri | http://hdl.handle.net/10722/196698 | - |
dc.description.abstract | In 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.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journals web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500 | - |
dc.relation.ispartof | IEEE International Conference on Neural Networks Proceedings | - |
dc.rights | ©2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. | - |
dc.title | Lighting direction estimation of a shaded image by a surface-input regression network | - |
dc.type | Conference_Paper | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1109/IJCNN.2007.4370955 | - |
dc.identifier.scopus | eid_2-s2.0-51749118059 | - |
dc.identifier.spage | 201 | - |
dc.identifier.epage | 206 | - |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 160603 amended | - |
dc.identifier.issnl | 1098-7576 | - |