Light field appearance manifolds

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2004.

Bibliographic Details
Main Author: Christoudias, Chris Mario, 1980-
Other Authors: Trevor Darrell.
Format: Thesis
Language:en_US
Published: Massachusetts Institute of Technology 2005
Subjects:
Online Access:http://hdl.handle.net/1721.1/28728
_version_ 1811072268558663680
author Christoudias, Chris Mario, 1980-
author2 Trevor Darrell.
author_facet Trevor Darrell.
Christoudias, Chris Mario, 1980-
author_sort Christoudias, Chris Mario, 1980-
collection MIT
description Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2004.
first_indexed 2024-09-23T09:03:14Z
format Thesis
id mit-1721.1/28728
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T09:03:14Z
publishDate 2005
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/287282019-04-10T20:28:46Z Light field appearance manifolds Christoudias, Chris Mario, 1980- Trevor Darrell. Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2004. Includes bibliographical references (leaves 137-141). Statistical shape and texture appearance models are powerful image representations, but previously had been restricted to 2D or 3D shapes with smooth surfaces and lambertian reflectance. In this thesis we present a novel 4D appearance model using image-based rendering techniques, which can represent complex lighting conditions, structures, and surfaces. We construct a light field manifold capturing the multi-view appearance of an object class and extend previous direct search algorithms to match new light fields or 2D images of an object to a point on this manifold. When matching to a 2D image the reconstructed light field can be used to render unseen views of the object. Our technique differs from previous view-based active appearance models in that model coefficients between views are explicitly linked, and that we do not model any pose variation within the deformable model at a single view. It overcomes the limitations of polygonal based appearance models and uses light fields that are acquired in real-time. by Chris Mario Christoudias. S.M. 2005-09-27T18:00:58Z 2005-09-27T18:00:58Z 2004 2004 Thesis http://hdl.handle.net/1721.1/28728 59554532 en_US M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 141 p. 6023817 bytes 6042420 bytes application/pdf application/pdf application/pdf Massachusetts Institute of Technology
spellingShingle Electrical Engineering and Computer Science.
Christoudias, Chris Mario, 1980-
Light field appearance manifolds
title Light field appearance manifolds
title_full Light field appearance manifolds
title_fullStr Light field appearance manifolds
title_full_unstemmed Light field appearance manifolds
title_short Light field appearance manifolds
title_sort light field appearance manifolds
topic Electrical Engineering and Computer Science.
url http://hdl.handle.net/1721.1/28728
work_keys_str_mv AT christoudiaschrismario1980 lightfieldappearancemanifolds