Skip to content

Latest commit

 

History

History
106 lines (80 loc) · 7.55 KB

README.md

File metadata and controls

106 lines (80 loc) · 7.55 KB

PersFormer: a New Baseline for 3D Laneline Detection

pipeline

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Li Chen∗†, Chonghao Sima, Yang Li, Zehan Zheng, Jiajie Xu, Xiangwei Geng, Hongyang Li, Conghui He, Jianping Shi, Yu Qiao, Junchi Yan. equal contributions. corresponding authors

Introduction

PWC

This repository is the PyTorch implementation for PersFormer.

PersFormer is an end-to-end monocular 3D lane detector with a novel Transformer-based spatial feature transformation module. Our model generates BEV features by attending to related front-view local regions with camera parameters as a reference. It adopts a unified 2D/3D anchor design and an auxiliary task to detect 2D/3D lanes simultaneously, enhancing the feature consistency and sharing the benefits of multi-task learning.

Changelog

  • 2022-11-3: Fix the evaluation pipeline bug and upload the best model of PersFormer on openlaneV1.1 for reproducibility. Other models are coming soon.
  • 2022-9-27: Update evaluation metrics, prune gt points by visibility before evaluation, detail can be found in related issue A question about prune_3d_lane_by_visibility; support Gen-LaneNet on OpenLane; support PersFormer on once dataset.
  • 2022-5-9: We compared our method on ONCES_3DLanes Dataset, where PersFormer also outperforms other methods.
  • 2022-4-12: We released the v1.0 code for PersFormer.

Get Started

Installation

  • To run PersFormer, make sure you are using a machine with at least one GPU.
  • Please follow INSTALL.md to setup the environment.

Dataset

  • Please refer to OpenLane for downloading OpenLane Dataset.
  • Please refer to Gen-LaneNet for downloading Apollo 3D Lane Synthetic Dataset.

Training and evaluation

  • Please follow TRAIN_VAL.md to train and evaluate the model.

Benchmark

  • 3D Lane Detection Results (F-Score) in OpenLane.
Method Version All Up &
Down
Curve Extreme
Weather
Night Intersection Merge&
Split
Best model x-c x-f z-c z-f Category Accuracy
GenLaneNet 1.1 32.3 25.4 33.5 28.1 18.7 21.4 31.0 - 0.593 0.494 0.140 0.195 /
3DLaneNet 1.1 44.1 40.8 46.5 47.5 41.5 32.1 41.7 - - - - - -
PersFormer 1.1 50.5 45.6 58.7 54.0 50.0 41.6 53.1 model 0.319 0.325 0.112 0.141 89.51
PersFormer 1.2 53.1 46.8 58.7 54.0 48.4 41.4 52.5 model 0.361 0.328 0.124 0.129 88.99
  • 2D Lane Detection Results (F-Score) in OpenLane. Note that the baseline of 2D branch in PersFormer is LaneATT.
Method All Up&
Down
Curve Extreme
Weather
Night Intersection Merge&
Split
LaneATT-S 28.3 25.3 25.8 32.0 27.6 14.0 24.3
LaneATT-M 31.0 28.3 27.4 34.7 30.2 17.0 26.5
PersFormer 42.0 40.7 46.3 43.7 36.1 28.9 41.2
CondLaneNet-S 52.3 55.3 57.5 45.8 46.6 48.4 45.5
CondLaneNet-M 55.0 58.5 59.4 49.2 48.6 50.7 47.8
CondLaneNet-L 59.1 62.1 62.9 54.7 51.0 55.7 52.3
Method F1(%) Precision(%) Recall(%) CD error(m) Best model
3DLaneNet 44.73 61.46 35.16 0.127 /
GenLaneNet 45.59 63.95 35.42 0.121 /
SALAD (paper of ONCE 3DLanes ) 64.07 75.90 55.42 0.098 /
PersFormer 72.07 77.82 67.11 0.086 model

Visualization

Following are the visualization results of PersFormer on OpenLane dataset and Apollo dataset.

  • OpenLane visualization results
    openlane_vis
  • Apollo 3D Synthetic visualization results
    apollo_vis

Citation

Please use the following citation if you find our repo or our paper PersFormer useful:

    @inproceedings{chen2022persformer,
      title={PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark},
      author={Chen, Li and Sima, Chonghao and Li, Yang and Zheng, Zehan and Xu, Jiajie and Geng, Xiangwei and Li, Hongyang and He, Conghui and Shi, Jianping and Qiao, Yu and Yan, Junchi},
      booktitle={European Conference on Computer Vision (ECCV)},
      year={2022}
    }  

Acknowledgements

We would like to acknowledge the great support from SenseBee labelling team at SenseTime Research, constructive suggestion from Zihan Ding at BUAA, and the fruitful discussions and comments for this project from Zhiqi Li, Yuenan Hou, Yu Liu, Jing Shao, Jifeng Dai. We thank for the code implementation from Gen-LaneNet, LaneATT and Deformable DETR.

License

All code within this repository is under Apache License 2.0.