<?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>2026-11-22T09:45:46Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/120906" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/120906</identifier><datestamp>2026-05-15T17:53:29Z</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">Cai, Ruojin</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair" lang="en_US">Snavely, Keith</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Hariharan, Bharath</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Marschner, Stephen</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Zhang, Cheng</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-04-02T18:52:04Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2026-04-02T18:52:04Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025-08</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 15215</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 32170536</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/120906</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/848s-9e12</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">17422536</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">209 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Understanding the 3D world from data collected by sensors such as cameras and LiDAR is a fundamental problem in computer vision, with applications in robotics, augmented and virtual reality, and autonomous systems. Although current algorithms can produce high-quality 3D reconstructions, they often struggle under real-world conditions, such as when data is sparse, visual overlap is limited, or scenes contain strong ambiguities like repetition and symmetry. This thesis explores how learned priors can help overcome these challenges and improve 3D spatial understanding. I begin by addressing the problem of shape generation and reconstruction from sparse point clouds, proposing a method that learns shape priors through modeling gradient fields over 3D point cloud distributions. Next, I tackle the challenge of extreme camera pose estimation between image pairs with little or no overlap, using dense correlation volumes to extract semantic and geometric cues. Building on this, I further improve extreme pose estimation by leveraging visual world priors from generative video models, which hallucinate plausible intermediate frames to provide useful context. Finally, I address visual ambiguity in structure-from-motion by using 3D priors from feature-matching models to disambiguate visually similar but incorrect matches, what we call “doppelgangers”, in symmetric scenes like the Arc de Triomphe.</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" lang="en_US">3D Computer Vision</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">3D Reconstruction</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Camera Pose Estimation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Generative Model</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Pushing the Boundaries of 3D Spatial Understanding</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Computer Science</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., Computer Science</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810.2</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://ecommons.cornell.edu/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Cai, Ruojin</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="86de20d6-3f4c-46dd-bde8-95e7f275137e">
	&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>Pushing the Boundaries of 3D Spatial Understanding&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2025-08&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/848s-9e12&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Cai, Ruojin&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 Computer Vision&lt;/Keyword>
    &lt;Keyword>3D Reconstruction&lt;/Keyword>
    &lt;Keyword>Camera Pose Estimation&lt;/Keyword>
    &lt;Keyword>Generative Model&lt;/Keyword>
   	&lt;Abstract>Understanding the 3D world from data collected by sensors such as cameras and LiDAR is a fundamental problem in computer vision, with applications in robotics, augmented and virtual reality, and autonomous systems. Although current algorithms can produce high-quality 3D reconstructions, they often struggle under real-world conditions, such as when data is sparse, visual overlap is limited, or scenes contain strong ambiguities like repetition and symmetry. This thesis explores how learned priors can help overcome these challenges and improve 3D spatial understanding. I begin by addressing the problem of shape generation and reconstruction from sparse point clouds, proposing a method that learns shape priors through modeling gradient fields over 3D point cloud distributions. Next, I tackle the challenge of extreme camera pose estimation between image pairs with little or no overlap, using dense correlation volumes to extract semantic and geometric cues. Building on this, I further improve extreme pose estimation by leveraging visual world priors from generative video models, which hallucinate plausible intermediate frames to provide useful context. Finally, I address visual ambiguity in structure-from-motion by using 3D priors from feature-matching models to disambiguate visually similar but incorrect matches, what we call “doppelgangers”, in symmetric scenes like the Arc de Triomphe.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>