Example Based Processing For Image And Video Synthesis

dc.contributor.advisor Essa, Irfan
dc.contributor.author Haro, Antonio en_US
dc.contributor.committeeMember Bobick, Aaron
dc.contributor.committeeMember Kang, Sing Bing
dc.contributor.committeeMember Rehg, James M.
dc.contributor.committeeMember Turk, Greg
dc.contributor.department Computing en_US
dc.date.accessioned 2005-03-04T16:42:15Z
dc.date.available 2005-03-04T16:42:15Z
dc.date.issued 2003-11-25 en_US
dc.description.abstract The example based processing problem can be expressed as: "Given an example of an image or video before and after processing, apply a similar processing to a new image or video". Our thesis is that there are some problems where a single general algorithm can be used to create varieties of outputs, solely by presenting examples of what is desired to the algorithm. This is valuable if the algorithm to produce the output is non-obvious, e.g. an algorithm to emulate an example painting's style. We limit our investigations to example based processing of images, video, and 3D models as these data types are easy to acquire and experiment with. We represent this problem first as a texture synthesis influenced sampling problem, where the idea is to form feature vectors representative of the data and then sample them coherently to synthesize a plausible output for the new image or video. Grounding the problem in this manner is useful as both problems involve learning the structure of training data under some assumptions to sample it properly. We then reduce the problem to a labeling problem to perform example based processing in a more generalized and principled manner than earlier techniques. This allows us to perform a different estimation of what the output should be by approximating the optimal (and possibly not known) solution through a different approach. en_US
dc.description.degree Ph.D. en_US
dc.format.extent 95308697 bytes
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/5283
dc.language.iso en_US
dc.publisher Georgia Institute of Technology en_US
dc.subject Markov random fields en_US
dc.subject Image-based rendering
dc.subject Learning from example
dc.subject Filter approximation
dc.subject Function approximation
dc.title Example Based Processing For Image And Video Synthesis en_US
dc.type Text
dc.type.genre Dissertation
dspace.entity.type Publication
local.contributor.advisor Essa, Irfan
local.contributor.corporatename College of Computing
relation.isAdvisorOfPublication 84ae0044-6f5b-4733-8388-4f6427a0f817
relation.isOrgUnitOfPublication c8892b3c-8db6-4b7b-a33a-1b67f7db2021
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
90.89 MB
Adobe Portable Document Format