PersFormer_3DLane and OpenLane
About PersFormer_3DLane
OpenDriveLab/PersFormer_3DLane
[ECCV 2022 Oral] Perspective Transformer on 3D Lane Detection
This helps autonomous vehicle developers accurately detect 3D lane lines from a single camera feed. It takes raw camera images as input and outputs precise 3D coordinates of lane markings, helping self-driving systems understand road structure. It's designed for engineers building robust perception systems for autonomous driving.
About OpenLane
OpenDriveLab/OpenLane
[ECCV 2022 Oral] OpenLane: Large-scale Realistic 3D Lane Dataset
This dataset provides a rich collection of real-world driving scenarios to help train and evaluate autonomous driving systems. It takes raw perception data from public datasets like Waymo and adds detailed annotations for 3D lanes and important objects in the vehicle's path. Engineers and researchers developing self-driving car technology can use this to improve how vehicles detect and understand road markings and critical obstacles.
Scores updated daily from GitHub, PyPI, and npm data. How scores work