<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v3.0 20080202//EN" "https://jats.nlm.nih.gov/nlm-dtd/publishing/3.0/journalpublishing3.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" dtd-version="3.0" xml:lang="en">
<front>
<journal-meta>
<journal-id journal-id-type="publisher">ISPRS-Archives</journal-id>
<journal-title-group>
<journal-title>ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences</journal-title>
<abbrev-journal-title abbrev-type="publisher">ISPRS-Archives</abbrev-journal-title>
<abbrev-journal-title abbrev-type="nlm-ta">Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.</abbrev-journal-title>
</journal-title-group>
<issn pub-type="epub">2194-9034</issn>
<publisher><publisher-name>Copernicus Publications</publisher-name>
<publisher-loc>Göttingen, Germany</publisher-loc>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="doi">10.5194/isprs-archives-XLII-2-W9-403-2019</article-id>
<title-group>
<article-title>GENERATIVE ADVERSARIAL NETWORKS FOR SINGLE PHOTO 3D RECONSTRUCTION</article-title>
</title-group>
<contrib-group><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Kniaz</surname>
<given-names>V. V.</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
</contrib>
<contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Remondino</surname>
<given-names>F.</given-names>
</name>
<xref ref-type="aff" rid="aff3">
<sup>3</sup>
</xref>
<ext-link>https://orcid.org/0000-0001-6097-5342</ext-link></contrib>
<contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Knyaz</surname>
<given-names>V. A.</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
</contrib>
</contrib-group><aff id="aff1">
<label>1</label>
<addr-line>State Res. Institute of Aviation Systems (GosNIIAS), 125319, 7, Victorenko str., Moscow, Russia</addr-line>
</aff>
<aff id="aff2">
<label>2</label>
<addr-line>Moscow Institute of Physics and Technology (MIPT), Russia</addr-line>
</aff>
<aff id="aff3">
<label>3</label>
<addr-line>3D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK), Trento, Italy</addr-line>
</aff>
<pub-date pub-type="epub">
<day>31</day>
<month>01</month>
<year>2019</year>
</pub-date>
<volume>XLII-2/W9</volume>
<fpage>403</fpage>
<lpage>408</lpage>
<permissions>
<license license-type="open-access">
<license-p>This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit <ext-link ext-link-type="uri" xlink:href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</ext-link></license-p>
</license>
</permissions>
<self-uri xlink:href="https://isprs-archives.copernicus.org/articles/isprs-archives-XLII-2-W9-403-2019.html">This article is available from https://isprs-archives.copernicus.org/articles/isprs-archives-XLII-2-W9-403-2019.html</self-uri>
<self-uri xlink:href="https://isprs-archives.copernicus.org/articles/isprs-archives-XLII-2-W9-403-2019.pdf">The full text article is available as a PDF file from https://isprs-archives.copernicus.org/articles/isprs-archives-XLII-2-W9-403-2019.pdf</self-uri>
<abstract>
<p>Fast but precise 3D reconstructions of cultural heritage scenes are becoming very requested in the archaeology and architecture. While modern multi-image 3D reconstruction approaches provide impressive results in terms of textured surface models, it is often the need to create a 3D model for which only a single photo (or few sparse) is available. This paper focuses on the single photo 3D reconstruction problem for lost cultural objects for which only a few images are remaining. We use image-to-voxel translation network (Z-GAN) as a starting point. Z-GAN network utilizes the skip connections in the generator network to transfer 2D features to a 3D voxel model effectively (Figure 1). Therefore, the network can generate voxel models of previously unseen objects using object silhouettes present on the input image and the knowledge obtained during a training stage. In order to train our Z-GAN network, we created a large dataset that includes aligned sets of images and corresponding voxel models of an ancient Greek temple. We evaluated the Z-GAN network for single photo reconstruction on complex structures like temples as well as on lost heritage still available in crowdsourced images. Comparison of the reconstruction results with state-of-the-art methods are also presented and commented.</p>
</abstract>
<counts><page-count count="6"/></counts>
</article-meta>
</front>
<body/>
<back>
</back>
</article>
