<?xml version="1.0" encoding="UTF-8"?>

<modsCollection xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd">
<mods version="3.3">

<genre>thesis</genre>

<titleInfo><title>Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis</title></titleInfo>


<note type="publicationStatus">published</note>

<note type="internalNote">CHe</note>



<name type="personal">
  <namePart type="given">Mohamed Khaled</namePart>
  <namePart type="family">Ashmawy</namePart>
  <role><roleTerm type="text">author</roleTerm> </role><identifier type="local">81286</identifier></name>
<name type="personal">
  <namePart type="given">Buse</namePart>
  <namePart type="family">Akay</namePart>
  <role><roleTerm type="text">author</roleTerm> </role><identifier type="local">88405</identifier></name>
<name type="personal">
  <namePart type="given">Alvaro</namePart>
  <namePart type="family">Balderrama</namePart>
  <role><roleTerm type="text">author</roleTerm> </role><identifier type="local">74171</identifier><description xsi:type="identifierDefinition" type="orcid">0000-0002-4118-2838</description></name>







<name type="corporate">
  <namePart></namePart>
  <identifier type="local">DEP1634</identifier>
  <role>
    <roleTerm type="text">department</roleTerm>
  </role>
</name>



<name type="conference">
  <namePart>44. eCAADe-Konferenz</namePart>
</name>






<abstract lang="eng">Deploying digital twins across the broader building stock is constrained by a key bottleneck: high-quality 3D content from LiDAR or photogrammetry remains labor-intensive and difficult to scale. We introduce Generative Twins (GT), a workflow that shifts digital twin creation from explicit geometric reconstruction toward probabilistic 3D synthesis. The pipeline takes a
single street-level façade photograph, corrects perspective distortion and removes occlusions, uses an instruction-conditioned multimodal image model to synthesise an isometric view of the building, and passes that view to an image-to-3D reconstruction model that leverages learned shape priors to produce a textured mesh without manual modelling. Three image to-3D platforms (Hitem3D, Hyper3D and Hunyuan3D 3.1) are compared on identical isometric inputs and assessed on architectural boundary clarity. We demonstrate GT through two applied cases: (i) reconstruction of ordinary residential streets in Detmold as stimuli for a virtual-reality study of multi sensory urban perception, and (ii) Green Editor, a design-exploration tool in which façade greenery is added or removed at the image layer before mesh generation.
Together these cases position Generative Twins as a scalable pathway for the digitization of ordinary building stock, with emphasis on controllability, editability, and iterative design workflows.</abstract>

<originInfo><publisher>eCAADe</publisher><dateIssued encoding="w3cdtf">2026</dateIssued><place><placeTerm type="text">Lübeck</placeTerm></place>
</originInfo>
<language><languageTerm authority="iso639-2b" type="code">eng</languageTerm>
</language>

<subject><topic>Digital Twins</topic><topic>Virtual Reality (VR</topic><topic>Artificial Intelligence (AI)</topic><topic>Image-to-3D</topic><topic>Generative Design.</topic>
</subject>


<relatedItem type="host"><titleInfo><title>eCAADe proceedings</title></titleInfo>
  <identifier type="issn">2684-1843</identifier><identifier type="doi">10.52842/conf.ecaade.2026.1.619</identifier>
<part><detail type="volume"><number>1</number></detail>
</part>
</relatedItem>


<extension>
<bibliographicCitation>
<havard>M.K. Ashmawy, B. Akay, A. Balderrama, Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis, eCAADe, 2026.</havard>
<chicago>Ashmawy, Mohamed Khaled, Buse Akay, and Alvaro Balderrama. &lt;i&gt;Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis&lt;/i&gt;. &lt;i&gt;ECAADe Proceedings&lt;/i&gt;. Vol. 1. eCAADe, 2026. &lt;a href=&quot;https://doi.org/10.52842/conf.ecaade.2026.1.619&quot;&gt;https://doi.org/10.52842/conf.ecaade.2026.1.619&lt;/a&gt;.</chicago>
<ama>Ashmawy MK, Akay B, Balderrama A. &lt;i&gt;Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis&lt;/i&gt;. Vol 1. eCAADe; 2026. doi:&lt;a href=&quot;https://doi.org/10.52842/conf.ecaade.2026.1.619&quot;&gt;10.52842/conf.ecaade.2026.1.619&lt;/a&gt;</ama>
<short>M.K. Ashmawy, B. Akay, A. Balderrama, Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis, eCAADe, 2026.</short>
<apa>Ashmawy, M. K., Akay, B., &amp;#38; Balderrama, A. (2026). Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis. In &lt;i&gt;eCAADe proceedings&lt;/i&gt; (Vol. 1). eCAADe. &lt;a href=&quot;https://doi.org/10.52842/conf.ecaade.2026.1.619&quot;&gt;https://doi.org/10.52842/conf.ecaade.2026.1.619&lt;/a&gt;</apa>
<van>Ashmawy MK, Akay B, Balderrama A. Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis. Vol. 1, eCAADe proceedings. eCAADe; 2026.</van>
<ieee>M. K. Ashmawy, B. Akay, and A. Balderrama, &lt;i&gt;Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis&lt;/i&gt;, vol. 1. eCAADe, 2026. doi: &lt;a href=&quot;https://doi.org/10.52842/conf.ecaade.2026.1.619&quot;&gt;10.52842/conf.ecaade.2026.1.619&lt;/a&gt;.</ieee>
<chicago-de>Ashmawy, Mohamed Khaled, Buse Akay und Alvaro Balderrama. 2026. &lt;i&gt;Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis&lt;/i&gt;. &lt;i&gt;eCAADe proceedings&lt;/i&gt;. Bd. 1. eCAADe. doi:&lt;a href=&quot;https://doi.org/10.52842/conf.ecaade.2026.1.619&quot;&gt;10.52842/conf.ecaade.2026.1.619&lt;/a&gt;, .</chicago-de>
<mla>Ashmawy, Mohamed Khaled, et al. “Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis.” &lt;i&gt;ECAADe Proceedings&lt;/i&gt;, vol. 1, eCAADe, 2026, &lt;a href=&quot;https://doi.org/10.52842/conf.ecaade.2026.1.619&quot;&gt;https://doi.org/10.52842/conf.ecaade.2026.1.619&lt;/a&gt;.</mla>
<ufg>&lt;b&gt;Ashmawy, Mohamed Khaled/Akay, Buse/Balderrama, Alvaro&lt;/b&gt;: Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis, Bd. 1, o. O. 2026.</ufg>
<bjps>&lt;b&gt;Ashmawy MK, Akay B and Balderrama A&lt;/b&gt; (2026) &lt;i&gt;Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis&lt;/i&gt;. eCAADe.</bjps>
<din1505-2-1>&lt;span style=&quot;font-variant:small-caps;&quot;&gt;Ashmawy, Mohamed Khaled&lt;/span&gt; ; &lt;span style=&quot;font-variant:small-caps;&quot;&gt;Akay, Buse&lt;/span&gt; ; &lt;span style=&quot;font-variant:small-caps;&quot;&gt;Balderrama, Alvaro&lt;/span&gt;: &lt;i&gt;Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis&lt;/i&gt;. Bd. 1 : eCAADe, 2026</din1505-2-1>
</bibliographicCitation>
</extension>
<recordInfo><recordIdentifier>14070</recordIdentifier><recordCreationDate encoding="w3cdtf">2026-09-30T10:14:15Z</recordCreationDate><recordChangeDate encoding="w3cdtf">2026-10-01T14:28:23Z</recordChangeDate>
</recordInfo>
</mods>
</modsCollection>
