Horizon Line Estimation On York Urban Dataset
Metrics
AUC (horizon error)
Results
Performance results of various models on this benchmark
| Paper Title | Code | ||
|---|---|---|---|
| V | 95.35 | A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws | |
| CNN+FULL | 94.78 | Detecting Vanishing Points using Global Image Context in a Non-Manhattan World | |
| DL-IGP | 94.27 | Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection | |
| GoogleNet (Huber Loss, horizon line projection) | 86.41 | Horizon Lines in the Wild |
0 of 4 row(s) selected.