OpenCodePapers

lane-detection-on-bdd100k-val

Lane Detection
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeIoU (%)Accuracy (%)Params (M)ModelNameReleaseDate
TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation✓ Link34.281.91.94TwinLiteNetPlus-Large2024-03-25
TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation✓ Link32.379.10.48TwinLiteNetPlus-Medium2024-03-25
HybridNets: End-to-End Perception Network✓ Link31.685.412.8HybridNets2022-03-17
TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars✓ Link31.0877.80.43TwinLiteNet2023-07-20
TriLiteNet: Lightweight Model for Multi-Task Visual Perception✓ Link29.882.32.35TriLiteNet-base2025-03-17
TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation✓ Link29.375.80.12TwinLiteNetPlus-Small2024-03-25
You Only Look at Once for Real-time and Generic Multi-Task✓ Link28.884.9A-YOLOM(s)2023-10-02
YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception✓ Link27.2587.838.9YOLOPv22022-08-24
YOLOP: You Only Look Once for Panoptic Driving Perception✓ Link26.270.57.9YOLOP2021-08-25
TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation✓ Link23.370.20.03TwinLiteNetPlus-Nano2024-03-25
Learning Lightweight Lane Detection CNNs by Self Attention Distillation✓ Link16.0236.6Enet-SAD2019-08-02
Check out how to contribute new results.