DL-IGP

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Horizon Line EstimationonHorizon Lines in the Wild
AUC (horizon error)· 2017-07-08
57.31
best: 54.43 (V)
SOTA
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection arXiv:1707.02427
Horizon Line EstimationonEurasian Cities Dataset
AUC (horizon error)· 2017-07-08
86.26
best: 83.6 (GoogleNet (Huber Loss, horizon line projection))
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection arXiv:1707.02427
Horizon Line EstimationonYork Urban Dataset
AUC (horizon error)· 2017-07-08
94.27
best: 86.41 (GoogleNet (Huber Loss, horizon line projection))
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection arXiv:1707.02427