Panorama Depth Estimation on Stanford2D3D 1.0 (area5)
0.0829MREPanelNet
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PanelNetInput Resolution=512 x 1024, Loss Function=Reverse Huber Loss (BerHu)2023.05 | 0.0829 | 0.152 | 0.2933 | 0.0579 | 92.42 | 97.96 | 99.15 | |
| HoHoNetInput Resolution=512 x 10242023.05 | 0.1014 | 0.2027 | 0.3834 | 0.0668 | 90.54 | 96.93 | 98.86 | |
| OmnifusionInput Resolution=512 x 10242023.05 | 0.1031 | 0.1958 | 0.3521 | 0.0698 | 89.13 | 97.02 | 98.75 | |
| SliceNetInput Resolution=512 x 10242023.05 | 0.1043 | 0.1838 | 0.3689 | 0.0771 | 90.34 | 96.45 | 98.64 | |
| BifuseInput Resolution=512 x 10242023.05 | 0.1209 | 0.2343 | 0.4142 | 0.0787 | 86.6 | 95.8 | 98.6 | |
| FCRNInput Resolution=512 x 10242023.05 | 0.1837 | 0.3428 | 0.5774 | 0.11 | 72.3 | 92.07 | 97.31 | |
| OmniDepthInput Resolution=512 x 10242023.05 | 0.1996 | 0.3743 | 0.6152 | 0.1212 | 68.77 | 88.91 | 95.78 |