CNN+FULL

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)· 2016-08-19
58.24
best: 54.43 (V)
SOTA
Detecting Vanishing Points using Global Image Context in a Non-Manhattan World arXiv:1608.05684
Horizon Line EstimationonEurasian Cities Dataset
AUC (horizon error)· 2016-08-19
90.8
best: 83.6 (GoogleNet (Huber Loss, horizon line projection))
Detecting Vanishing Points using Global Image Context in a Non-Manhattan World arXiv:1608.05684
Horizon Line EstimationonYork Urban Dataset
AUC (horizon error)· 2016-08-19
94.78
best: 86.41 (GoogleNet (Huber Loss, horizon line projection))
Detecting Vanishing Points using Global Image Context in a Non-Manhattan World arXiv:1608.05684