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

TL;DR

Pano3D introduces a comprehensive benchmark for 360-degree depth estimation from spherical panoramas, evaluating accuracy, boundary preservation, and generalization across datasets, providing a solid baseline for future research.

Contribution

It presents a holistic benchmark for 360-degree depth estimation, including inter-dataset evaluation and analysis of classical methods, establishing a solid baseline for future work.

Findings

Benchmark assesses all depth traits including generalization.

Classical methods analyzed for insights into depth estimation.

Provides a solid baseline for panoramic depth estimation.

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 to unseen data into different test splits, Pano3D represents a holistic benchmark for $360^o$ 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.