Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection
We present a novel approach for vanishing point detection from uncalibrated monocular images. In contrast to state-of-the-art, we make no a priori assumptions about the observed scene. Our method is based on a convolutional neural network (CNN) which does not use natural images, but a Gaussian sphere representation arising from an inverse gnomonic projection of lines detected in an image. This allows us to rely on synthetic data for training, eliminating the need for labelled images. Our method achieves competitive performance on three horizon estimation benchmark datasets. We further highlight some additional use cases for which our vanishing point detection algorithm can be used.
PDF Abstract
Datasets
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Horizon Line Estimation | Eurasian Cities Dataset | DL-IGP | AUC (horizon error) | 86.26 | # 3 | |
| Horizon Line Estimation | Horizon Lines in the Wild | DL-IGP | AUC (horizon error) | 57.31 | # 4 | |
| Horizon Line Estimation | York Urban Dataset | DL-IGP | AUC (horizon error) | 94.27 | # 3 |
Methods
No methods listed for this paper. Add
relevant methods here
