Dataset Restricted Access
Pano3D: GibsonV2 Full High Resolution
Albanis, Georgios;
Zioulis, Nikolaos;
Drakoulis, Petros;
Gkitsas, Vasileios;
Sterzentsenko, Vladimiros;
Alvarez, Federico;
Zarpalas, Dimitrios;
Daras, Petros
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.
Restricted Access
You may request access to the files in this upload, provided that you fulfil the conditions below. The decision whether to grant/deny access is solely under the responsibility of the record owner.
The Pano3D dataset is a derivative of other datasets of 3D scanned buildings.
To download the Pano3D dataset we follow a two-step process:
- Access to the Pano3D 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 request form.
- 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 download page). 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.
| All versions | This version | |
|---|---|---|
| Views | 369 | 369 |
| Downloads | 256 | 256 |
| Data volume | 1.1 TB | 1.1 TB |
| Unique views | 261 | 261 |
| Unique downloads | 63 | 63 |
- Publication date:
- June 18, 2021
- DOI:
-
- Keyword(s):
- 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
- Grants:
-
European Commission:
- ATLANTIS - AuThoring tooL for indoor Augmented and dimiNished realiTy experIenceS (951900)
- Meeting:
- IEEE Computer Vision and Pattern Recognition Conference (CVPR), Online, Virtual, 19-25 June 2021
- Communities: