Abstract | ||
---|---|---|
A novel learnable line segment detector and descriptor is proposed which allows efficient extraction and matching of 2D lines via the angular distance of 128 dimensional unit descriptor vectors. While many handcrafted and deep features have been proposed for keypoints, only a few methods exist for line segments. It is well known, however, that line segments are commonly found in man-made environme... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/3DV53792.2021.00054 | 2021 International Conference on 3D Vision (3DV) |
Keywords | DocType | ISSN |
Line detector,Line descriptor,Pose estimation,CNNs | Conference | 2378-3826 |
ISBN | Citations | PageRank |
978-1-6654-2688-6 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hichem Abdellali | 1 | 0 | 1.01 |
Robert Frohlich | 2 | 8 | 1.56 |
Viktor Vilagos | 3 | 0 | 0.34 |
Zoltan Kato | 4 | 265 | 28.28 |