Monocular Panoramic Depth Estimation on Matterport3D (official)
0.1471MAENeural Contourlet Network
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Neural Contourlet NetworkBackbone=ResNet50, Input Resolution=512x1024, Parameters=60M2022.08 | 0.1471 | 0.0786 | 0.3799 | 0.0469 | 90.48 | 97.86 | 99.26 | |
| Unifuse2022.08 | 0.2814 | — | 0.4941 | 0.0701 | 88.97 | 96.23 | 98.31 | |
| HoHoNet2022.08 | 0.2862 | 0.1488 | 0.5138 | 0.0871 | 87.86 | 95.19 | 97.71 | |
| SliceNet2022.08 | 0.3296 | 0.1764 | 0.6133 | 0.1045 | 87.16 | 94.83 | 97.16 | |
| Bifuse2022.08 | 0.347 | 0.2048 | 0.6259 | 0.1134 | 84.52 | 93.19 | 96.32 | |
| FCRN2022.08 | 0.4008 | 0.2409 | 0.6704 | 0.1244 | 77.03 | 91.74 | 96.17 | |
| OmniDepth2022.08 | 0.4838 | 0.2901 | 0.7643 | 0.145 | 68.3 | 87.94 | 94.29 |