Name
Abstract | ||
|---|---|---|
Pano3D is a new benchmark for depth estimation from spherical panoramas. It aims to assess performance across all depth estimation traits, the primary direct depth estimation performance targeting precision and accuracy, and also the secondary traits, boundary preservation and smoothness. Moreover, Pano3D moves beyond typical intra-dataset evaluation to inter-dataset performance assessment. By disentangling the capacity to generalize in unseen data into different test splits, Pano3D represents a holistic benchmark for 360 degrees depth estimation. We use it as a basis for an extended analysis seeking to offer insights into classical choices for depth estimation. This results into a solid baseline for panoramic depth that followup works can built upon to steer future progress. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPRW53098.2021.00413 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Georgios Albanis | 1 | 0 | 1.01 |
| Nikolaos Zioulis | 2 | 34 | 10.15 |
| Petros Drakoulis | 3 | 2 | 2.76 |
| Vasileios Gkitsas | 4 | 0 | 1.01 |
| Vladimiros Sterzentsenko | 5 | 3 | 3.12 |
| Federico Alvarez | 6 | 10 | 1.86 |
| Dimitrios Zarpalas | 7 | 303 | 33.96 |
| Petros Daras | 8 | 1129 | 131.72 |