Dataset Restricted Access

Pano3D: GibsonV2 Full High Resolution

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


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.4986012", 
  "language": "eng", 
  "title": "Pano3D: GibsonV2 Full High Resolution", 
  "issued": {
    "date-parts": [
      [
        2021, 
        6, 
        18
      ]
    ]
  }, 
  "abstract": "<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>", 
  "author": [
    {
      "family": "Albanis, Georgios"
    }, 
    {
      "family": "Zioulis, Nikolaos"
    }, 
    {
      "family": "Drakoulis, Petros"
    }, 
    {
      "family": "Gkitsas, Vasileios"
    }, 
    {
      "family": "Sterzentsenko, Vladimiros"
    }, 
    {
      "family": "Alvarez, Federico"
    }, 
    {
      "family": "Zarpalas, Dimitrios"
    }, 
    {
      "family": "Daras, Petros"
    }
  ], 
  "id": "4986012", 
  "note": "Dataset with coupled color and depth maps.(normals are not included but may be provided upon request)", 
  "event-place": "Online, Virtual", 
  "version": "1.0", 
  "type": "dataset", 
  "event": "IEEE Computer Vision and Pattern Recognition Conference (CVPR)"
}
437
449
views
downloads
All versions This version
Views 437437
Downloads 449449
Data volume 1.9 TB1.9 TB
Unique views 305305
Unique downloads 7979

Share

Cite as