<?xml version='1.0' encoding='utf-8'?>
<eprints xmlns='http://eprints.org/ep2/data/2.0'>
  <eprint id='https://researchdata.bath.ac.uk/id/eprint/922'>
    <eprintid>922</eprintid>
    <rev_number>64</rev_number>
    <documents>
      <document id='https://researchdata.bath.ac.uk/id/document/13719'>
        <docid>13719</docid>
        <rev_number>3</rev_number>
        <files>
          <file id='https://researchdata.bath.ac.uk/id/file/43095'>
            <fileid>43095</fileid>
            <datasetid>document</datasetid>
            <objectid>13719</objectid>
            <filename>Preprocessed.zip</filename>
            <mime_type>application/zip</mime_type>
            <hash>45b42e4c5ef7d6340a2dd768512bbce8</hash>
            <hash_type>MD5</hash_type>
            <filesize>3432648006</filesize>
            <mtime>2020-12-04 10:56:35</mtime>
            <url>https://researchdata.bath.ac.uk/922/3/Preprocessed.zip</url>
          </file>
        </files>
        <eprintid>922</eprintid>
        <pos>3</pos>
        <placement>3</placement>
        <mime_type>application/zip</mime_type>
        <format>other</format>
        <formatdesc>A directory containing preprocessed datasets. These contain the optical flow, csv files and meshes necessary to render the scene using the viewer in our software.</formatdesc>
        <language>en</language>
        <security>staffonly</security>
        <license>cc_by</license>
        <main>Preprocessed.zip</main>
        <content>data</content>
      </document>
      <document id='https://researchdata.bath.ac.uk/id/document/13720'>
        <docid>13720</docid>
        <rev_number>3</rev_number>
        <files>
          <file id='https://researchdata.bath.ac.uk/id/file/43098'>
            <fileid>43098</fileid>
            <datasetid>document</datasetid>
            <objectid>13720</objectid>
            <filename>Unprocessed.zip</filename>
            <mime_type>application/zip</mime_type>
            <hash>c501d62be82e50ca2f195e7972e7b508</hash>
            <hash_type>MD5</hash_type>
            <filesize>18721248314</filesize>
            <mtime>2020-12-04 11:04:33</mtime>
            <url>https://researchdata.bath.ac.uk/922/4/Unprocessed.zip</url>
          </file>
        </files>
        <eprintid>922</eprintid>
        <pos>4</pos>
        <placement>4</placement>
        <mime_type>application/zip</mime_type>
        <format>other</format>
        <formatdesc>A directory containing unprocessed datasets. These will need to be pre-processed using the omniphotos code and also contain the raw mp4/insv video files with the yaml files used to generate the input images for the datasets.</formatdesc>
        <language>en</language>
        <security>staffonly</security>
        <license>cc_by</license>
        <main>Unprocessed.zip</main>
        <content>data</content>
      </document>
    </documents>
    <eprint_status>archive</eprint_status>
    <userid>11561</userid>
    <dir>disk0/00/00/09/22</dir>
    <datestamp>2020-12-07 11:05:05</datestamp>
    <lastmod>2024-07-22 14:26:48</lastmod>
    <status_changed>2020-12-07 11:05:05</status_changed>
    <type>data_collection</type>
    <metadata_visibility>no_search</metadata_visibility>
    <creators>
      <item>
        <name>
          <family>Bertel</family>
          <given>Tobias</given>
        </name>
        <id>T.B.Bertel@bath.ac.uk</id>
        <affiliation>University of Bath</affiliation>
        <contact>FALSE</contact>
      </item>
      <item>
        <name>
          <family>Yuan</family>
          <given>Mingze</given>
        </name>
        <id>mzy22@bath.ac.uk</id>
        <affiliation>University of Bath</affiliation>
        <contact>FALSE</contact>
      </item>
      <item>
        <name>
          <family>Lindroos</family>
          <given>Reuben</given>
        </name>
        <id>rjl67@bath.ac.uk</id>
        <affiliation>University of Bath</affiliation>
        <contact>TRUE</contact>
      </item>
      <item>
        <name>
          <family>Richardt</family>
          <given>Christian</given>
        </name>
        <id>C.Richardt@bath.ac.uk</id>
        <orcid>0000-0001-6716-9845</orcid>
        <affiliation>University of Bath</affiliation>
        <contact>TRUE</contact>
      </item>
    </creators>
    <title>Datasets for “OmniPhotos: Casual 360° VR Photography”</title>
    <divisions>
      <item>dept_compsci</item>
    </divisions>
    <keywords>Virtual Reality, Novel View Synthesis, Casual Capture, Image-Based Rendering, Motion Parallax</keywords>
    <abstract>This dataset contains the raw and processed data used to validate the results for the paper. Each subdirectory in the Preprocessed and Unprocessed folders contains a 360° video captured in a circle at different locations in the world, using an Insta360 One X 360° camera on a rotating selfie stick. These subdirectories are named after these locations. Both the proprietary (.insv) video format, as well as a stitched equirectangular (.mp4) video (used by our preprocessing pipeline), have been included. As well as these videos, each subdirectory contains the Input frames, used by our software to display the scene, a Capture directory that contains structure-from-motion data for the given scene, as well as a Config directory, which contains necessary configuration files to run our software.

In the Preprocessed directory, the subdirectories also contain a Cache directory, containing optical flow (.floss) files, a CSV file linking the floss files to the relevant images in Input, and .obj files that contain the scene-dependent proxy mesh (deformed sphere) used to render the scene.</abstract>
    <date>2020-11-26</date>
    <publisher>University of Bath</publisher>
    <full_text_status>restricted</full_text_status>
    <corp_contributors>
      <item>
        <type>RightsHolder</type>
        <corpname>University of Bath</corpname>
      </item>
    </corp_contributors>
    <funding>
      <item>
        <funder_name>Engineering and Physical Sciences Research Council</funder_name>
        <funder_id>https://doi.org/10.13039/501100000266</funder_id>
        <grant_id>EP/S001050/1</grant_id>
        <project_name>Fellowship - Towards Immersive 360° VR Video with Motion Parallax</project_name>
      </item>
    </funding>
    <research_centres>
      <item>cent_dig_ent</item>
      <item>cent_camera</item>
    </research_centres>
    <collection_method>Full details of the methodology may be found in the associated paper.</collection_method>
    <methodurl>
      <item>https://researchportal.bath.ac.uk/en/publications/634ba8f1-e7bb-4133-b9be-a99ddcc3b4a2</item>
    </methodurl>
    <language>en</language>
    <version>1</version>
    <doi>10.15125/BATH-00922</doi>
    <related_resources>
      <item>
        <link>https://doi.org/10.1145/3414685.3417770</link>
        <type>pub</type>
      </item>
    </related_resources>
    <access_types>
      <item>request</item>
    </access_types>
    <access_arrangements>In this version, the first scene in Preprocessed.zip (&quot;Ballintoy&quot;) is missing the fitted scene-adaptive proxy geometry, and the scene &quot;Crescent&quot; in Unpreprocessed.zip contains an incorrect number of frames in the config file. Please refer to version 2 of the dataset for the corrected files.</access_arrangements>
  </eprint>
</eprints>
