Pano3D: Matterport3D (/w Filmic) Low Resolution
收藏资源简介:
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像(spherical panoramas)深度估计(depth estimation)任务的新型基准评测数据集。其旨在以统一且全面的路径推动该任务的技术发展。为达成这一目标,我们构建了全新的数据集,并整合了多维度评测指标——这些指标不仅可评估深度估计性能,还能兼顾边界保留(boundary preservation)和平滑度(smoothness)等次级特性。此外,Pano3D突破了传统的数据集内评测范式,转而支持跨数据集性能评估。我们将泛化能力拆解为三个不同维度,使得Pano3D能够在不同的训练外数据场景下实现合理的外推性能评估。依托这款面向360°深度估计的Pano3D全面评测基准,我们开展了扩展性分析,并为该任务确立了可靠的性能基线。




