Pano3D: A Holistic Benchmark and a Solid Baseline for 360deg Depth Estimation

Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis, Vasileios Gkitsas, Vladimiros Sterzentsenko, Federico Alvarez, Dimitrios Zarpalas, Petros Daras; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 3727-3737

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 intro-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 depth estimation. We use it as a basis for an extended analysis seeking to offer insights into classical choices for depth estimation. This results in a solid baseline for panoramic depth that follow-up works can build upon to steer future progress

Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Albanis_2021_CVPR, author = {Albanis, Georgios and Zioulis, Nikolaos and Drakoulis, Petros and Gkitsas, Vasileios and Sterzentsenko, Vladimiros and Alvarez, Federico and Zarpalas, Dimitrios and Daras, Petros}, title = {Pano3D: A Holistic Benchmark and a Solid Baseline for 360deg Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3727-3737} }