Pano3D: GibsonV2 Tiny-Fullplus Filmic High Resolution

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.Pano3D是一款面向球面全景图深度估计（depth estimation）任务的全新基准评测集。其核心目标是以统一且全面的方式推动该任务的研究进展。为达成这一目标，我们构建了全新的数据集，并集成了可同时覆盖深度估计性能、边界保留度（boundary preservation）与平滑度（smoothness）等辅助特性的评测指标体系。此外，Pano3D突破了传统的数据集内（intra-dataset）评测范式，转而支持跨数据集（inter-dataset）性能评估。我们将泛化能力（generalization）拆解为三个不同维度，使得Pano3D能够在不同的训练域外数据场景下开展合理的外推性能评估。基于这款面向360°深度估计的全方位评测基准Pano3D，我们开展了拓展性分析，并为该任务确立了可靠的性能基准基线。