Dataset Restricted Access

Pano3D: GibsonV2 Tiny-Medium-Fullplus High Resolution

Albanis, Georgios; Zioulis, Nikolaos; Drakoulis, Petros; Gkitsas, Vasileios; Sterzentsenko, Vladimiros; Alvarez, Federico; Zarpalas, Dimitrios; Daras, Petros


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Albanis, Georgios</dc:creator>
  <dc:creator>Zioulis, Nikolaos</dc:creator>
  <dc:creator>Drakoulis, Petros</dc:creator>
  <dc:creator>Gkitsas, Vasileios</dc:creator>
  <dc:creator>Sterzentsenko, Vladimiros</dc:creator>
  <dc:creator>Alvarez, Federico</dc:creator>
  <dc:creator>Zarpalas, Dimitrios</dc:creator>
  <dc:creator>Daras, Petros</dc:creator>
  <dc:date>2021-06-19</dc:date>
  <dc:description>Pano3D is a new benchmark for depth estimation from spherical panoramas. Its goal is to drive progress for this task in a consistent and holistic manner. To achieve that we generate a new dataset and integrate evaluation metrics that capture not only depth performance, but also secondary traits like boundary preservation and smoothness. Moreover, Pano3D takes a step beyond typical intra-dataset evaluation schemes to inter-dataset performance assessment. By disentangling generalization to three different axes, Pano3D facilitates proper extrapolation assessment under different out-of-training data conditions. Relying on the Pano3D holistic benchmark for 360 depth estimation we perform an extended analysis and derive a solid baseline for the task.</dc:description>
  <dc:description>Dataset with coupled color and depth maps.(normals are not included but may be provided upon request)</dc:description>
  <dc:identifier>https://zenodo.org/record/4991961</dc:identifier>
  <dc:identifier>10.5281/zenodo.4991961</dc:identifier>
  <dc:identifier>oai:zenodo.org:4991961</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:relation>info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Innovation action/951900/</dc:relation>
  <dc:relation>doi:10.5281/zenodo.4991960</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/atlantis-ar</dc:relation>
  <dc:rights>info:eu-repo/semantics/restrictedAccess</dc:rights>
  <dc:subject>Spherical Depth Estimation</dc:subject>
  <dc:subject>Spherical Panoramas</dc:subject>
  <dc:subject>Omnidirectional Dataset</dc:subject>
  <dc:subject>Benchmark</dc:subject>
  <dc:subject>360</dc:subject>
  <dc:subject>Computer Vision</dc:subject>
  <dc:subject>Deep Learning</dc:subject>
  <dc:subject>Data-driven Methods</dc:subject>
  <dc:subject>3D Vision</dc:subject>
  <dc:subject>Depth Estimation</dc:subject>
  <dc:subject>Geometry Estimation</dc:subject>
  <dc:subject>Surface Orientation Estimation</dc:subject>
  <dc:subject>Indoor Scenes</dc:subject>
  <dc:subject>Scene Understanding</dc:subject>
  <dc:title>Pano3D: GibsonV2 Tiny-Medium-Fullplus High Resolution</dc:title>
  <dc:type>info:eu-repo/semantics/other</dc:type>
  <dc:type>dataset</dc:type>
</oai_dc:dc>
257
529
views
downloads
All versions This version
Views 257257
Downloads 529529
Data volume 1.1 TB1.1 TB
Unique views 194194
Unique downloads 109109

Share

Cite as