<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T10:30:18Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/102958" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/102958</identifier><datestamp>2026-05-15T19:51:33Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Poursaeed, Omid</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair">Belongie, Serge J.</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember">Joachims, Thorsten</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember">Zabih, Ramin</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2021-03-12T17:39:54Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-03-12T17:39:54Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2020-08</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 12239</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 28088959</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/102958</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/my1j-4c82</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">13277989</dim:field>
   <dim:field mdschema="dc" element="description">186 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Deep Learning has made tremendous progress in the last decade, making breakthroughs in visual perception and imagination. Discriminative models have achieved human-level performance on several tasks. Generative models have also shown great promise for 2D and 3D synthesis; however, their performance still lags behind discriminative models. Several approaches have been proposed to enhance the performance of generative models. One promising direction is leveraging multiple representations to guide the synthesis process. In this dissertation, we explore how generative models can benefit from hybrid representations, in which a stronger representation guides a weaker one. We propose models for 3D synthesis conditioned on images or point clouds, label-conditioned 2D generation, and 2.5D motion generation. A major drawback of current generative models is that they require gigantic datasets for training. We present a few-shot synthesis method for decreasing the model’s dependence on labeled data. Finally, we discuss adversarial applications of generative models in which adversaries abuse visual realism to deceive humans and machines.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights">Attribution 4.0 International</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">https://creativecommons.org/licenses/by/4.0/</dim:field>
   <dim:field mdschema="dc" element="subject">3D Deep Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Adversarial Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Computer Vision</dim:field>
   <dim:field mdschema="dc" element="subject">Deep Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Generative Models</dim:field>
   <dim:field mdschema="dc" element="subject">Machine Learning</dim:field>
   <dim:field mdschema="dc" element="title">Hybrid Generative Models for 2D and 3D Computer Vision</dim:field>
   <dim:field mdschema="dc" element="type">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="localuri">https://catalog.library.cornell.edu/catalog/13277989</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Doctor of Philosophy</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">Ph. D., Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://cornell-ecommons.eks.prod.4science.cloud/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Poursaeed, Omid</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d2140dfe-fe0c-4185-8fd6-fc052825a23a">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en&lt;/Language>
   	&lt;Title>Hybrid Generative Models for 2D and 3D Computer Vision&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2020-08&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/my1j-4c82&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Poursaeed, Omid&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;License>https://creativecommons.org/licenses/by/4.0/&lt;/License>
    &lt;Keyword>3D Deep Learning&lt;/Keyword>
    &lt;Keyword>Adversarial Learning&lt;/Keyword>
    &lt;Keyword>Computer Vision&lt;/Keyword>
    &lt;Keyword>Deep Learning&lt;/Keyword>
    &lt;Keyword>Generative Models&lt;/Keyword>
    &lt;Keyword>Machine Learning&lt;/Keyword>
   	&lt;Abstract>Deep Learning has made tremendous progress in the last decade, making breakthroughs in visual perception and imagination. Discriminative models have achieved human-level performance on several tasks. Generative models have also shown great promise for 2D and 3D synthesis; however, their performance still lags behind discriminative models. Several approaches have been proposed to enhance the performance of generative models. One promising direction is leveraging multiple representations to guide the synthesis process. In this dissertation, we explore how generative models can benefit from hybrid representations, in which a stronger representation guides a weaker one. We propose models for 3D synthesis conditioned on images or point clouds, label-conditioned 2D generation, and 2.5D motion generation. A major drawback of current generative models is that they require gigantic datasets for training. We present a few-shot synthesis method for decreasing the model’s dependence on labeled data. Finally, we discuss adversarial applications of generative models in which adversaries abuse visual realism to deceive humans and machines.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>