The MIT Libraries is completing a major upgrade to DSpace@MIT.
Starting May 5 2026, DSpace will remain functional, viewable, searchable, and downloadable, however, you will not be able to edit existing collections or add new material.
We are aiming to have full functionality restored by May 18, 2026, but intermittent service interruptions may occur.
Please email dspace-lib@mit.edu with any questions.
Thank you for your patience as we implement this important upgrade.
Light Field Morphable Models
| dc.contributor.author | Christoudias, Chris Mario | en_US |
| dc.contributor.author | Morency, Louis-Philippe | en_US |
| dc.contributor.author | Darrell, Trevor | en_US |
| dc.date.accessioned | 2004-10-08T20:38:54Z | |
| dc.date.available | 2004-10-08T20:38:54Z | |
| dc.date.issued | 2003-04-18 | en_US |
| dc.identifier.other | AIM-2003-010 | en_US |
| dc.identifier.uri | http://hdl.handle.net/1721.1/6716 | |
| dc.description.abstract | Statistical shape and texture appearance models are powerful image representations, but previously had been restricted to 2D or simple 3D shapes. In this paper we present a novel 3D morphable model based on image-based rendering techniques, which can represent complex lighting conditions, structures, and surfaces. We describe how to construct a manifold of the multi-view appearance of an object class using light fields and show how to match a 2D image of an object to a point on this manifold. In turn we use the reconstructed light field to render novel views of the object. Our technique overcomes the limitations of polygon based appearance models and uses light fields that are acquired in real-time. | en_US |
| dc.format.extent | 1375810 bytes | |
| dc.format.extent | 716555 bytes | |
| dc.format.mimetype | application/postscript | |
| dc.format.mimetype | application/pdf | |
| dc.language.iso | en_US | |
| dc.relation.ispartofseries | AIM-2003-010 | en_US |
| dc.subject | AI | en_US |
| dc.title | Light Field Morphable Models | en_US |
