{"url":"/task/lane-detection","name":"Lane Detection","slug":"lane-detection","description_markdown":"**Lane Detection** is a computer vision task that involves identifying the boundaries of driving lanes in a video or image of a road scene. The goal is to accurately locate and track the lane markings in real-time, even in challenging conditions such as poor lighting, glare, or complex road layouts. \r\n\r\nLane detection is an important component of advanced driver assistance systems (ADAS) and autonomous vehicles, as it provides information about the road layout and the position of the vehicle within the lane, which is crucial for navigation and safety. The algorithms typically use a combination of computer vision techniques, such as edge detection, color filtering, and Hough transforms, to identify and track the lane markings in a road scene.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [End-to-end Lane Detection\r\n](https://github.com/wvangansbeke/LaneDetection_End2End) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":251,"papers_with_code":103,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/lane-detection-on-culane","slug":"lane-detection-on-culane","dataset":"CULane","dataset_url":"/dataset/culane","rows_in_archive":63,"metrics":["F1 score","mF1"],"first_row_in_archive_order":{"model":"DLNet","paper_title":"DLNet: Direction-Aware Feature Integration for Robust Lane Detection in Complex Environments","paper_url":"/paper/dlnet-direction-aware-feature-integration-for","paper_date":"2025-06-09","arxiv_id":null,"code_links":[{"title":"RDXiaoLu/DLNet","url":"https://github.com/RDXiaoLu/DLNet"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-tusimple","slug":"lane-detection-on-tusimple","dataset":"TuSimple","dataset_url":"/dataset/tusimple","rows_in_archive":43,"metrics":["Accuracy","F1 score"],"first_row_in_archive_order":{"model":"SCNN_UNet_Attention_PL*","paper_title":"Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss","paper_url":"/paper/robust-lane-detection-through-self-pre","paper_date":"2023-05-26","arxiv_id":"2305.17271","code_links":[],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-curvelanes","slug":"lane-detection-on-curvelanes","dataset":"CurveLanes","dataset_url":"/dataset/curvelanes","rows_in_archive":19,"metrics":["F1 score","GFLOPs","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"CondLSTR (ResNet-101)","paper_title":"Generating Dynamic Kernels via Transformers for Lane Detection","paper_url":"/paper/generating-dynamic-kernels-via-transformers","paper_date":"2023-01-01","arxiv_id":null,"code_links":[{"title":"czyczyyzc/CondLSTR","url":"https://github.com/czyczyyzc/CondLSTR"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-bdd100k-val","slug":"lane-detection-on-bdd100k-val","dataset":"BDD100K val","dataset_url":"/dataset/bdd100k","rows_in_archive":11,"metrics":["IoU (%)","Accuracy (%)","Params (M)"],"first_row_in_archive_order":{"model":"TwinLiteNetPlus-Large","paper_title":"TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation","paper_url":"/paper/twinlitenetplus-a-stronger-model-for-real","paper_date":"2024-03-25","arxiv_id":"2403.16958","code_links":[{"title":"chequanghuy/TwinLiteNet","url":"https://github.com/chequanghuy/TwinLiteNet"},{"title":"chequanghuy/TwinLiteNetPlus","url":"https://github.com/chequanghuy/TwinLiteNetPlus"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-llamas","slug":"lane-detection-on-llamas","dataset":"LLAMAS","dataset_url":"/dataset/llamas","rows_in_archive":10,"metrics":["F1","mF1"],"first_row_in_archive_order":{"model":"CLRNet (DLA-34)","paper_title":"CLRNet: Cross Layer Refinement Network for Lane Detection","paper_url":"/paper/clrnet-cross-layer-refinement-network-for","paper_date":"2022-03-19","arxiv_id":"2203.10350","code_links":[{"title":"Turoad/lanedet","url":"https://github.com/Turoad/lanedet"},{"title":"Turoad/clrnet","url":"https://github.com/Turoad/clrnet"},{"title":"zkyseu/PPlanedet","url":"https://github.com/zkyseu/PPlanedet"},{"title":"zkyntu/UnLanedet","url":"https://github.com/zkyntu/UnLanedet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/lane-detection-on-nuscenes","slug":"lane-detection-on-nuscenes","dataset":"nuScenes","dataset_url":"/dataset/nuscenes","rows_in_archive":3,"metrics":["IoU","F1 score"],"first_row_in_archive_order":{"model":"DSLP","paper_title":"Learning to Predict Navigational Patterns from Partial Observations","paper_url":"/paper/learning-to-predict-navigational-patterns","paper_date":"2023-04-26","arxiv_id":"2304.13242","code_links":[{"title":"robin-karlsson0/dslp","url":"https://github.com/robin-karlsson0/dslp"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-openlane","slug":"lane-detection-on-openlane","dataset":"OpenLane","dataset_url":"/dataset/openlane","rows_in_archive":3,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"CondLSTR (ResNet-18)","paper_title":"Generating Dynamic Kernels via Transformers for Lane Detection","paper_url":"/paper/generating-dynamic-kernels-via-transformers","paper_date":"2023-01-01","arxiv_id":null,"code_links":[{"title":"czyczyyzc/CondLSTR","url":"https://github.com/czyczyyzc/CondLSTR"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-caltech-lanes-cordova","slug":"lane-detection-on-caltech-lanes-cordova","dataset":"Caltech Lanes Cordova","dataset_url":null,"rows_in_archive":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"VPGNet","paper_title":"VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition","paper_url":"/paper/vpgnet-vanishing-point-guided-network-for","paper_date":"2017-10-17","arxiv_id":"1710.06288","code_links":[{"title":"SeokjuLee/VPGNet","url":"https://github.com/SeokjuLee/VPGNet"},{"title":"cciprianmihai/Self_Driving_Car_NanoDegree_P2_AdvancedLaneLines","url":"https://github.com/cciprianmihai/Self_Driving_Car_NanoDegree_P2_AdvancedLaneLines"},{"title":"Ceachi/Project-Self-Driving-Car-Advanced-Lane-Lines","url":"https://github.com/Ceachi/Project-Self-Driving-Car-Advanced-Lane-Lines"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/lane-detection-on-caltech-lanes-washington","slug":"lane-detection-on-caltech-lanes-washington","dataset":"Caltech Lanes Washington","dataset_url":null,"rows_in_archive":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"VPGNet","paper_title":"VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition","paper_url":"/paper/vpgnet-vanishing-point-guided-network-for","paper_date":"2017-10-17","arxiv_id":"1710.06288","code_links":[{"title":"SeokjuLee/VPGNet","url":"https://github.com/SeokjuLee/VPGNet"},{"title":"cciprianmihai/Self_Driving_Car_NanoDegree_P2_AdvancedLaneLines","url":"https://github.com/cciprianmihai/Self_Driving_Car_NanoDegree_P2_AdvancedLaneLines"},{"title":"Ceachi/Project-Self-Driving-Car-Advanced-Lane-Lines","url":"https://github.com/Ceachi/Project-Self-Driving-Car-Advanced-Lane-Lines"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/lane-detection-on-det","slug":"lane-detection-on-det","dataset":"DET","dataset_url":"/dataset/det","rows_in_archive":1,"metrics":["Average IOU","event-based F1 score"],"first_row_in_archive_order":{"model":"LDNet","paper_title":"LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision Sensor","paper_url":"/paper/ldnet-end-to-end-lane-detection-approach","paper_date":"2020-09-17","arxiv_id":"2009.08020","code_links":[{"title":"likui01/LDNet","url":"https://github.com/likui01/LDNet"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-k-lane","slug":"lane-detection-on-k-lane","dataset":"K-Lane","dataset_url":"/dataset/k-lane","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"LLDN-GFC","paper_title":"K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways","paper_url":"/paper/mixer-based-lidar-lane-detection-network-and","paper_date":"2021-10-21","arxiv_id":"2110.11048","code_links":[{"title":"kaist-avelab/k-lane","url":"https://github.com/kaist-avelab/k-lane"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":2}}},{"leaderboard":"/sota/lane-detection-on-openlane-v2-val","slug":"lane-detection-on-openlane-v2-val","dataset":"OpenLane-V2 val","dataset_url":"/dataset/openlane-v2","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"TopoLogic","paper_title":"TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes","paper_url":"/paper/topologic-an-interpretable-pipeline-for-lane","paper_date":"2024-05-23","arxiv_id":"2405.14747","code_links":[{"title":"franpin/topologic","url":"https://github.com/franpin/topologic"},{"title":"franpin/topopoint","url":"https://github.com/franpin/topopoint"}],"syntology":null}},{"leaderboard":"/sota/lane-detection-on-tvtlane","slug":"lane-detection-on-tvtlane","dataset":"tvtLane","dataset_url":null,"rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"SCNN_UNet_Attention_PL*","paper_title":"Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss","paper_url":"/paper/robust-lane-detection-through-self-pre","paper_date":"2023-05-26","arxiv_id":"2305.17271","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/nuscenes","name":"nuScenes","full_name":"","num_papers_in_archive":2139},{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/culane","name":"CULane","full_name":"","num_papers_in_archive":85},{"url":"/dataset/tusimple","name":"TuSimple","full_name":"","num_papers_in_archive":76},{"url":"/dataset/openlane","name":"OpenLane","full_name":"","num_papers_in_archive":46},{"url":"/dataset/curvelanes","name":"CurveLanes","full_name":"","num_papers_in_archive":19},{"url":"/dataset/once-3dlanes","name":"ONCE-3DLanes","full_name":"Monocular 3D Lane Detection Dataset","num_papers_in_archive":12},{"url":"/dataset/comma-2k19","name":"comma 2k19","full_name":"","num_papers_in_archive":11},{"url":"/dataset/openlane-v2","name":"OpenLane-V2 val","full_name":"","num_papers_in_archive":11},{"url":"/dataset/vil-100","name":"VIL-100","full_name":"","num_papers_in_archive":9},{"url":"/dataset/llamas","name":"LLAMAS","full_name":"Labeled Lane Markers","num_papers_in_archive":6},{"url":"/dataset/elas","name":"ELAS","full_name":"","num_papers_in_archive":5},{"url":"/dataset/carlane-benchmark","name":"CARLANE Benchmark","full_name":"","num_papers_in_archive":4},{"url":"/dataset/k-lane","name":"K-Lane","full_name":"KAIST-Lane","num_papers_in_archive":4},{"url":"/dataset/tusimple-lane","name":"TuSimple Lane","full_name":"","num_papers_in_archive":3},{"url":"/dataset/assisttaxi","name":"AssistTaxi","full_name":"","num_papers_in_archive":2},{"url":"/dataset/det","name":"DET","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-lane-detection","name":"3D Lane Detection"}],"parent_tasks":[{"url":"/task/autonomous-vehicles","name":"Autonomous Vehicles"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":103,"tagged_in_all":251,"items":[{"url":"/paper/end-to-end-learning-for-self-driving-cars","title":"End to End Learning for Self-Driving Cars","date":"2016-04-25","arxiv_id":"1604.07316","repositories_listed":113,"syntology":{"n":41,"n_ran":9,"n_unverified":32,"n_pointer_only":9}},{"url":"/paper/towards-end-to-end-lane-detection-an-instance","title":"Towards End-to-End Lane Detection: an Instance Segmentation Approach","date":"2018-02-15","arxiv_id":"1802.05591","repositories_listed":22,"syntology":{"n":34,"n_ran":3,"n_unverified":31,"n_pointer_only":1}},{"url":"/paper/ultra-fast-structure-aware-deep-lane","title":"Ultra Fast Structure-aware Deep Lane Detection","date":"2020-04-24","arxiv_id":"2004.11757","repositories_listed":10,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/key-points-estimation-and-point-instance","title":"Key Points Estimation and Point Instance Segmentation Approach for Lane Detection","date":"2020-02-16","arxiv_id":"2002.06604","repositories_listed":10,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/spatial-as-deep-spatial-cnn-for-traffic-scene","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","date":"2017-12-17","arxiv_id":"1712.06080","repositories_listed":9,"syntology":null},{"url":"/paper/semantic-instance-segmentation-with-a","title":"Semantic Instance Segmentation with a Discriminative Loss Function","date":"2017-08-08","arxiv_id":"1708.02551","repositories_listed":8,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/yolop-you-only-look-once-for-panoptic-driving","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","date":"2021-08-25","arxiv_id":"2108.11250","repositories_listed":5,"syntology":{"n":18,"n_ran":1,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/clrnet-cross-layer-refinement-network-for","title":"CLRNet: Cross Layer Refinement Network for Lane Detection","date":"2022-03-19","arxiv_id":"2203.10350","repositories_listed":4,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/condlanenet-a-top-to-down-lane-detection","title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","date":"2021-05-11","arxiv_id":"2105.05003","repositories_listed":4,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/resa-recurrent-feature-shift-aggregator-for","title":"RESA: Recurrent Feature-Shift Aggregator for Lane Detection","date":"2020-08-31","arxiv_id":"2008.13719","repositories_listed":4,"syntology":null},{"url":"/paper/bdd100k-a-diverse-driving-video-database-with","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","date":"2018-05-12","arxiv_id":"1805.04687","repositories_listed":4,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/end-to-end-lane-detection-with-one-to-several","title":"End-to-End Lane detection with One-to-Several Transformer","date":"2023-05-01","arxiv_id":"2305.00675","repositories_listed":3,"syntology":null},{"url":"/paper/hybridnets-end-to-end-perception-network-1","title":"HybridNets: End-to-End Perception Network","date":"2022-03-17","arxiv_id":"2203.09035","repositories_listed":3,"syntology":null},{"url":"/paper/keep-your-eyes-on-the-lane-attention-guided","title":"Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection","date":"2020-10-22","arxiv_id":"2010.12035","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/vpgnet-vanishing-point-guided-network-for","title":"VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition","date":"2017-10-17","arxiv_id":"1710.06288","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/topopoint-enhance-topology-reasoning-via","title":"TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving","date":"2025-05-23","arxiv_id":"2505.17771","repositories_listed":2,"syntology":null},{"url":"/paper/topologic-an-interpretable-pipeline-for-lane","title":"TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes","date":"2024-05-23","arxiv_id":"2405.14747","repositories_listed":2,"syntology":null},{"url":"/paper/twinlitenetplus-a-stronger-model-for-real","title":"TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation","date":"2024-03-25","arxiv_id":"2403.16958","repositories_listed":2,"syntology":null},{"url":"/paper/lane2seq-towards-unified-lane-detection-via","title":"Lane2Seq: Towards Unified Lane Detection via Sequence Generation","date":"2024-02-27","arxiv_id":"2402.17172","repositories_listed":2,"syntology":null},{"url":"/paper/adnet-lane-shape-prediction-via-anchor","title":"ADNet: Lane Shape Prediction via Anchor Decomposition","date":"2023-08-21","arxiv_id":"2308.10481","repositories_listed":2,"syntology":null},{"url":"/paper/contrastive-learning-for-lane-detection-via","title":"Contrastive Learning for Lane Detection via cross-similarity","date":"2023-08-16","arxiv_id":"2308.08242","repositories_listed":2,"syntology":null},{"url":"/paper/clrernet-improving-confidence-of-lane","title":"CLRerNet: Improving Confidence of Lane Detection with LaneIoU","date":"2023-05-15","arxiv_id":"2305.08366","repositories_listed":2,"syntology":null},{"url":"/paper/yolopv2-better-faster-stronger-for-panoptic","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","date":"2022-08-24","arxiv_id":"2208.11434","repositories_listed":2,"syntology":null},{"url":"/paper/ultra-fast-deep-lane-detection-with-hybrid","title":"Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification","date":"2022-06-15","arxiv_id":"2206.07389","repositories_listed":2,"syntology":null},{"url":"/paper/once-3dlanes-building-monocular-3d-lane","title":"ONCE-3DLanes: Building Monocular 3D Lane Detection","date":"2022-04-30","arxiv_id":"2205.00301","repositories_listed":2,"syntology":null},{"url":"/paper/a-keypoint-based-global-association-network","title":"A Keypoint-based Global Association Network for Lane Detection","date":"2022-04-15","arxiv_id":"2204.07335","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/eigenlanes-data-driven-lane-descriptors-for","title":"Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes","date":"2022-03-29","arxiv_id":"2203.15302","repositories_listed":2,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/persformer-3d-lane-detection-via-perspective-1","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","date":"2022-03-21","arxiv_id":"2203.11089","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/rethinking-efficient-lane-detection-via-curve","title":"Rethinking Efficient Lane Detection via Curve Modeling","date":"2022-03-04","arxiv_id":"2203.02431","repositories_listed":2,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/sim-to-real-domain-adaptation-for-lane","title":"Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving","date":"2022-02-15","arxiv_id":"2202.07133","repositories_listed":2,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}