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

Pano3D

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.

Publication
In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Click the Cite button above to copy/download publication metadata (*.bib).
Nikolaos Zioulis
Nikolaos Zioulis
Computer Vision, Graphics & Machine Learning R&D Engineer

My research interests lie at the intersection of computer vision, computer graphics and modern data-driven approaches.

Related