no code implementations • 6 Feb 2023 • Leonid Erlygin, Vladimir Zholobov, Valeriia Baklanova, Evgeny Sokolovskiy, Alexey Zaytsev
This study proposes a new method for uncertainty estimation based on the surrogate Gaussian process model.
1 code implementation • 10 Sep 2022 • Lev Teplyakov, Leonid Erlygin, Evgeny Shvets
We point out systematic inconsistencies in the annotations of popular line detection benchmarks - Wireframe and York Urban, carefully reannotate a subset of images and show that (i) existing detectors have improved quality on updated annotations without retraining, suggesting that new annotations correlate better with the notion of correct line segment detection; (ii) the gap between accuracies of our detector and others diminishes to negligible 0. 2 Fh , with our method being the fastest.
Ranked #4 on Line Segment Detection on wireframe dataset (FH metric)