Dataset Restricted Access

Pano3D: GibsonV2 Full High Resolution

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


JSON Export

{
  "owners": [
    48074
  ], 
  "doi": "10.5281/zenodo.4986012", 
  "stats": {
    "version_unique_downloads": 74.0, 
    "unique_views": 301.0, 
    "views": 433.0, 
    "version_views": 433.0, 
    "unique_downloads": 74.0, 
    "version_unique_views": 301.0, 
    "volume": 1769037495866.0, 
    "version_downloads": 425.0, 
    "downloads": 425.0, 
    "version_volume": 1769037495866.0
  }, 
  "links": {
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.4986011.svg", 
    "doi": "https://doi.org/10.5281/zenodo.4986012", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.4986011", 
    "latest_html": "https://zenodo.org/record/4986012", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.4986012.svg", 
    "html": "https://zenodo.org/record/4986012", 
    "latest": "https://zenodo.org/api/records/4986012"
  }, 
  "conceptdoi": "10.5281/zenodo.4986011", 
  "created": "2021-06-20T13:44:00.787995+00:00", 
  "updated": "2021-06-21T01:48:24.062265+00:00", 
  "conceptrecid": "4986011", 
  "revision": 3, 
  "id": 4986012, 
  "metadata": {
    "access_right_category": "danger", 
    "doi": "10.5281/zenodo.4986012", 
    "version": "1.0", 
    "language": "eng", 
    "title": "Pano3D: GibsonV2 Full High Resolution", 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.4986011", 
        "relation": "isVersionOf"
      }
    ], 
    "notes": "Dataset with coupled color and depth maps.(normals are not included but may be provided upon request)", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4986011"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4986012"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "atlantis-ar"
      }
    ], 
    "access_conditions": "<p>The Pano3D dataset is a derivative of other datasets of 3D scanned buildings.</p>\n\n<p>To download the&nbsp;Pano3D&nbsp;dataset we follow a two-step process:</p>\n\n<ol>\n\t<li>Access to the&nbsp;Pano3D&nbsp;dataset requires agreement with the terms and conditions for each of the 3D datasets that were used to create (i.e. render) it, and more specifically, Matterport3D and GibsonV2. Therefore, in order to grant you access to this dataset, we need you to first fill&nbsp;<a href=\"https://forms.gle/SJUqLZYmu8sogwrAA\">request form</a>.</li>\n\t<li>Then, you need to perform a request for access to the respective Zenodo repositories, where the data are hosted (more information can be found in our&nbsp;<a href=\"https://vcl3d.github.io/Pano3D/download/\">download page</a>). Due to data-size limitations, the dataset is split into six (6) repositories, which respectively contain the color image, depth and normal map renders for each image. The repositories are split into the two resolutions, with each subgroup of 3 repositories containing the entire Matterport3D dataset renders, the entire GibsonV2 test split renders, and the remainder of GibsonV2 which is used as additional training data. Therefore, a separate request for access needs to be made to each repository in order to download the corresponding data.</li>\n</ol>", 
    "grants": [
      {
        "code": "951900", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::951900"
        }, 
        "title": "AuThoring tooL for indoor Augmented and dimiNished realiTy experIenceS", 
        "acronym": "ATLANTIS", 
        "program": "Horizon 2020 Framework Programme - Innovation action", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "Spherical Depth Estimation", 
      "Spherical Panoramas", 
      "Omnidirectional Dataset", 
      "Benchmark", 
      "360", 
      "Computer Vision", 
      "Deep Learning", 
      "Data-driven Methods", 
      "3D Vision", 
      "Depth Estimation", 
      "Geometry Estimation", 
      "Surface Orientation Estimation", 
      "Indoor Scenes", 
      "Scene Understanding"
    ], 
    "publication_date": "2021-06-18", 
    "creators": [
      {
        "orcid": "0000-0002-2032-6767", 
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Albanis, Georgios"
      }, 
      {
        "orcid": "0000-0002-7898-9344", 
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Zioulis, Nikolaos"
      }, 
      {
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Drakoulis, Petros"
      }, 
      {
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Gkitsas, Vasileios"
      }, 
      {
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Sterzentsenko, Vladimiros"
      }, 
      {
        "affiliation": "Universidad Polit\u00e9cnica de Madrid", 
        "name": "Alvarez, Federico"
      }, 
      {
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Zarpalas, Dimitrios"
      }, 
      {
        "affiliation": "Centre for Research and Technology Hellas", 
        "name": "Daras, Petros"
      }
    ], 
    "meeting": {
      "acronym": "CVPR", 
      "url": "http://cvpr2021.thecvf.com/", 
      "dates": "19-25 June 2021", 
      "place": "Online, Virtual", 
      "title": "IEEE Computer Vision and Pattern Recognition Conference"
    }, 
    "access_right": "restricted", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "description": "<p>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,&nbsp;Pano3D&nbsp;takes a step beyond typical intra-dataset evaluation schemes to inter-dataset performance assessment. By disentangling generalization to three different axes,&nbsp;Pano3D&nbsp;facilitates proper extrapolation assessment under different out-of-training data conditions. Relying on the&nbsp;Pano3D&nbsp;holistic benchmark for 360 depth estimation we perform an extended analysis and derive a solid baseline for the task.</p>"
  }
}
433
425
views
downloads
All versions This version
Views 433433
Downloads 425425
Data volume 1.8 TB1.8 TB
Unique views 301301
Unique downloads 7474

Share

Cite as