Pano3D: GibsonV2 Full High Resolution
Description
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.
Resources
| Name |
Format |
Description |
Link |
|
0 |
|
http://data.europa.eu/88u/dataset/oai-zenodo-org-4986012 |
Tags
- 360
- 3d-vision
- omnidirectional-dataset
- scene-understanding
- deep-learning
- spherical-depth-estimation
- benchmark
- depth-estimation
- geometry-estimation
- computer-vision
- surface-orientation-estimation
- data-driven-methods
- indoor-scenes
- spherical-panoramas