Please use this identifier to cite or link to this item:
https://doi.org/10.1109/ICIP.2005.1530313
DC Field | Value | |
---|---|---|
dc.title | Direct filtering method for image based rendering | |
dc.contributor.author | Kubota A. | |
dc.contributor.author | Aizawa K. | |
dc.contributor.author | Chen T. | |
dc.date.accessioned | 2018-08-21T05:09:39Z | |
dc.date.available | 2018-08-21T05:09:39Z | |
dc.date.issued | 2005 | |
dc.identifier.citation | Kubota A., Aizawa K., Chen T. (2005). Direct filtering method for image based rendering. Proceedings - International Conference on Image Processing, ICIP 3 : 1-4. ScholarBank@NUS Repository. https://doi.org/10.1109/ICIP.2005.1530313 | |
dc.identifier.isbn | 0780391349 | |
dc.identifier.isbn | 9780780391345 | |
dc.identifier.issn | 15224880 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/146307 | |
dc.description.abstract | Image based rendering (IBR) is basically a light ray resampling method for generating a novel image without aliasing artifacts from a given set of sampled light rays. To avoid aliasing artifacts, conventional methods require an estimate of the scene geometry. In this paper, we present a novel IBR method by linear filtering without estimating the scene geometry, for the simplified case when generating a virtual image at the center of 2x2 sparse camera array for a two depth-layers scene. The reconstruction filter used in the proposed method can derived by integrating all the process in our previously proposed method into an one-shot process. | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | OFFICE OF THE PROVOST | |
dc.contributor.department | DEPARTMENT OF COMPUTER SCIENCE | |
dc.description.doi | 10.1109/ICIP.2005.1530313 | |
dc.description.sourcetitle | Proceedings - International Conference on Image Processing, ICIP | |
dc.description.volume | 3 | |
dc.description.page | 1-4 | |
dc.published.state | published | |
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.