3D Lane Detection On Openlane V2 2
Metrics
DET_l
DET_t
OLS
TOP_ll
TOP_lt
Results
Performance results of various models on this benchmark
Model Name | DET_l | DET_t | OLS | TOP_ll | TOP_lt | Paper Title | Repository |
|---|---|---|---|---|---|---|---|
| TopoMLP | 28.8 | 53.3 | 41.2 | 7.8 | 30.1 | TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning | |
| Separated RoadTopoFormer | 26.95 | 61.4 | 43.6 | 15.4 | 21.8 | Separated RoadTopoFormer | - |
| VectorMapNet | 11.1 | 41.7 | 20.8 | 0.4 | 5.9 | VectorMapNet: End-to-end Vectorized HD Map Learning | |
| MapTR | 8.3 | 43.5 | 20.0 | 0.2 | 5.9 | MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction | |
| TopoBDA | 51.2 | 52.0 | 58.7 | 39.8 | 42.0 | TopoBDA: Towards Bezier Deformable Attention for Road Topology Understanding | - |
| TopoMask | 22.1 | 58.2 | 36.0 | 5.8 | 15.5 | TopoMask: Instance-Mask-Based Formulation for the Road Topology Problem via Transformer-Based Architecture | - |
| MFV | 35.3 | 79.9 | 53.3 | 23.0 | 33.3 | - | - |
| TopoNet | 28.5 | 48.1 | 35.6 | 4.1 | 20.8 | Graph-based Topology Reasoning for Driving Scenes | |
| TopoMaskV2 | 34.5 | 53.8 | 49.9 | 25.7 | 36.7 | TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem | - |
0 of 9 row(s) selected.