Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/69887
DC Field | Value | |
---|---|---|
dc.title | Detecting discontinuities for surface reconstruction | |
dc.contributor.author | Wang, Y. | |
dc.contributor.author | Bu, J. | |
dc.contributor.author | Li, N. | |
dc.contributor.author | Song, M. | |
dc.contributor.author | Tan, P. | |
dc.date.accessioned | 2014-06-19T03:05:47Z | |
dc.date.available | 2014-06-19T03:05:47Z | |
dc.date.issued | 2012 | |
dc.identifier.citation | Wang, Y.,Bu, J.,Li, N.,Song, M.,Tan, P. (2012). Detecting discontinuities for surface reconstruction. Proceedings - International Conference on Pattern Recognition : 2108-2111. ScholarBank@NUS Repository. | |
dc.identifier.isbn | 9784990644109 | |
dc.identifier.issn | 10514651 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/69887 | |
dc.description.abstract | Photometric stereo algorithms produce a map of normal directions from the input images. The 3D surface can be reconstructed from this normal map. Existing surface reconstruction works often assume the normal map is integrable but contaminated by small scale non-integrable noise. However, real surfaces often contain large discontinuities such as occlusion boundaries and sharp depth changes, which break the integrable assumption commonly made in many works. Here, we propose a method to detect these discontinuities by combining multiple geometric cues with trained classifiers and a simple graph optimization. The surface is then reconstructed with the guidance of these detected discontinuities. Experiments show our method outperforms existing works. © 2012 ICPR Org Committee. | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.description.sourcetitle | Proceedings - International Conference on Pattern Recognition | |
dc.description.page | 2108-2111 | |
dc.description.coden | PICRE | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.