Line Segment Detection On Wireframe Dataset
Metrics
sAP10
sAP5
Results
Performance results of various models on this benchmark
Model Name | sAP10 | sAP5 | Paper Title | Repository |
|---|---|---|---|---|
| MCMLSD | 10.4 | 7.6 | MCMLSD: A Dynamic Programming Approach to Line Segment Detection | - |
| F-Clip | 68.3 | 64.3 | Fully Convolutional Line Parsing | |
| HAWP | 66.5 | 62.5 | Holistically-Attracted Wireframe Parsing | |
| HT-HAWP | 66.6 | 62.9 | Deep Hough-Transform Line Priors | |
| ELSD | 68.9 | 64.3 | ELSD: Efficient Line Segment Detector and Descriptor | - |
| TP-LSD | 57.2 | 57.6 | TP-LSD: Tri-Points Based Line Segment Detector | - |
| ULSD | 66.4 | - | ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras | |
| L-CNN | 62.9 | 58.9 | End-to-End Wireframe Parsing | |
| LSDNet | - | - | LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection | |
| M-LSD | 62.1 | 56.4 | Towards Light-weight and Real-time Line Segment Detection |
0 of 10 row(s) selected.