Albanis, Georgios
Zioulis, Nikolaos
Drakoulis, Petros
Gkitsas, Vasileios
Sterzentsenko, Vladimiros
Alvarez, Federico
Zarpalas, Dimitrios
Daras, Petros
2021-06-19
<p>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.</p>
Dataset with coupled color and depth maps.(normals are not included but may be provided upon request)
https://doi.org/10.5281/zenodo.4991961
oai:zenodo.org:4991961
eng
Zenodo
https://zenodo.org/communities/atlantis-ar
https://doi.org/10.5281/zenodo.4991960
info:eu-repo/semantics/restrictedAccess
CVPR, IEEE Computer Vision and Pattern Recognition Conference, Online, Virtual, 19-25 June 2021
Spherical Depth Estimation
Spherical Panoramas
Omnidirectional Dataset
Benchmark
360
Computer Vision
Deep Learning
Data-driven Methods
3D Vision
Depth Estimation
Geometry Estimation
Surface Orientation Estimation
Indoor Scenes
Scene Understanding
Pano3D: GibsonV2 Tiny-Medium-Fullplus High Resolution
info:eu-repo/semantics/other