| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Monocular Depth Estimation | Stanford2D3D (test) | δ1 Accuracy97.27 | 71 | |
| Semantic Segmentation | Stanford2D3D Panoramic 1.0 (Fold-1) | mIoU54.2 | 43 | |
| Semantic Segmentation | Stanford2D3D-Panoramic (SPan) v1 (averaged by 3 folds) | mIoU54.1 | 39 | |
| Semantic Segmentation | Stanford2D3D | mIoU67.16 | 32 | |
| Semantic Segmentation | Stanford2D3D official (3-fold average) | mIoU0.6306 | 20 | |
| Semantic Segmentation | Stanford2D3D Pinhole (fold-1) | mIoU51.48 | 18 | |
| 360 Depth Estimation | Stanford2D3D 1.0 (test) | Abs Rel Error0.0679 | 14 | |
| Monocular panoramic depth estimation | Stanford2D3D | Delta 1 Accuracy93.94 | 13 | |
| Depth Estimation | Stanford2D3D | Abs Rel0.095 | 13 | |
| Semantic Segmentation | Stanford2D3D fold-1 (Area 5a and 5b) | mIoU45.73 | 12 | |
| Perspective Field prediction | Stanford2D3D (test) | Up Mean2.18 | 12 | |
| 360° layout estimation | Stanford2D3D (test) | 3D IoU86.6 | 11 | |
| Semantic Segmentation | Stanford2D3D official (Fold 1) | mIoU0.6737 | 10 | |
| Semantic Segmentation | Stanford2D3D (Area 5b) | mIoU45.73 | 9 | |
| Semantic Segmentation | Stanford2D3D (test) | mIoU69.47 | 9 | |
| Dense Depth Estimation | Stanford2D3D layout-available | RMSE0.394 | 8 | |
| 360 Layout Estimation | Stanford2D3D | 2D IoU88.37 | 8 | |
| Semantic Segmentation | Stanford2D3D sphere rank 7 256x512 (test) | Accuracy88.6 | 7 | |
| Depth Estimation | Stanford2D3D sphere rank 7 256x512 (test) | MAE0.165 | 7 | |
| Panorama Depth Estimation | Stanford2D3D 1.0 (area5) | MRE0.0829 | 7 | |
| Monocular 360 Depth Estimation | Stanford2D3D Area 5 (test) | MAE0.2027 | 7 | |
| Depth estimation | Stanford2D3D (fold-1 test) | MRE0.1014 | 6 | |
| Semantic Segmentation | Stanford2D3D Panoramic SGA (val fold 1) | mIoU65.04 | 6 | |
| Semantic Segmentation | Stanford2D3D Panoramic SPan8 | mIoU63.73 | 6 | |
| Surface Normal Estimation | Stanford2D3D (test) | Mean Angular Error9.706 | 5 |