{"id":{"repo_id":"gatech","oai_identifier":"oai:repository.gatech.edu:1853/5283"},"canonical_url":"https://search.dev.ndltd.org/etd/gatech/oai:repository.gatech.edu:1853/5283","repository":{"repo_id":"gatech","name":"Georgia Tech","base_url":"https://repository.gatech.edu/server/oai/request"},"display":{"title":"Example Based Processing For Image And Video Synthesis","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.","abstract_html":"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.","abstract_has_math":false,"creators":["Haro, Antonio"],"institution":"Georgia Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Computing","school":null,"contributors":[],"advisors":["Essa, Irfan"],"committee_chairs":[],"committee_members":["Bobick, Aaron","Kang, Sing Bing","Rehg, James M.","Turk, Greg"],"year":2003,"date_issued":"2003-11-25","date_published":"2003-11-25","updated_at":"2026-07-27T19:51:43Z","subjects":["Markov random fields","Image-based rendering","Learning from example","Filter approximation","Function approximation"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1853/5283","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Essa, Irfan"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Bobick, Aaron","Kang, Sing Bing","Rehg, James M.","Turk, Greg"]},{"key":"dc:contributor.department","label":"Department","values":["Computing"]},{"key":"dc:creator","label":"Author","values":["Haro, Antonio"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2005-03-04T16:42:15Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2005-03-04T16:42:15Z"]},{"key":"dc:date.issued","label":"Date","values":["2003-11-25"]},{"key":"dc:publisher","label":"Institution","values":["Georgia Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Markov random fields","Image-based rendering","Learning from example","Filter approximation","Function approximation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1853/5283"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Example Based Processing For Image And Video Synthesis"]}]}],"canonical_facts":{"dc:contributor.advisor":["Essa, Irfan"],"dc:contributor.committeemember":["Bobick, Aaron","Kang, Sing Bing","Rehg, James M.","Turk, Greg"],"dc:contributor.department":["Computing"],"dc:creator":["Haro, Antonio"],"dc:date.accessioned":["2005-03-04T16:42:15Z"],"dc:date.available":["2005-03-04T16:42:15Z"],"dc:date.issued":["2003-11-25"],"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."],"dc:description.degree":["Ph.D."],"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"],"dc:subject":["Markov random fields","Image-based rendering","Learning from example","Filter approximation","Function approximation"],"dc:title":["Example Based Processing For Image And Video Synthesis"],"dc:type":["Text"]},"updated_at":"2026-07-27T19:51:43Z"}