{"url":"/task/road-segementation","name":"Road Segmentation","slug":"road-segementation","description_markdown":"Road Segmentation is a pixel wise binary classification in order to extract underlying road network. Various Heuristic and data driven models are proposed. Continuity and robustness still remains one of the major challenges in the area.","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":82,"papers_with_code":34,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":5,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/road-segmentation-on-chesapeakersc","slug":"road-segmentation-on-chesapeakersc","dataset":"ChesapeakeRSC","dataset_url":"/dataset/chesapeakersc","rows_in_archive":4,"metrics":["DWR"],"first_row_in_archive_order":{"model":"U-Net (ResNet-18)","paper_title":"Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery","paper_url":"/paper/seeing-the-roads-through-the-trees-a","paper_date":"2024-01-12","arxiv_id":"2401.06762","code_links":[{"title":"isaaccorley/chesapeakersc","url":"https://github.com/isaaccorley/chesapeakersc"},{"title":"isaaccorley/resize-is-all-you-need","url":"https://github.com/isaaccorley/resize-is-all-you-need"}],"syntology":null}},{"leaderboard":"/sota/road-segementation-on-deepglobe","slug":"road-segementation-on-deepglobe","dataset":"DeepGlobe","dataset_url":"/dataset/deepglobe","rows_in_archive":3,"metrics":["APLS","IoU","mIoU"],"first_row_in_archive_order":{"model":"SPIN Road Mapper (ours)","paper_title":"SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving","paper_url":"/paper/spin-road-mapper-extracting-roads-from-aerial","paper_date":"2021-09-16","arxiv_id":"2109.07701","code_links":[{"title":"wgcban/spin_roadmapper","url":"https://github.com/wgcban/spin_roadmapper"}],"syntology":null}},{"leaderboard":"/sota/road-segementation-on-massachusetts-roads","slug":"road-segementation-on-massachusetts-roads","dataset":"Massachusetts Roads Dataset","dataset_url":"/dataset/massachusetts-roads-dataset","rows_in_archive":2,"metrics":["IoU","F1","APLS"],"first_row_in_archive_order":{"model":"RSM-SS","paper_title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","paper_url":"/paper/rs-mamba-for-large-remote-sensing-image-dense","paper_date":"2024-04-03","arxiv_id":"2404.02668","code_links":[{"title":"walking-shadow/Official_Remote_Sensing_Mamba","url":"https://github.com/walking-shadow/Official_Remote_Sensing_Mamba"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}}}],"datasets":[{"url":"/dataset/deepglobe","name":"DeepGlobe","full_name":"","num_papers_in_archive":127},{"url":"/dataset/massachusetts-roads-dataset","name":"Massachusetts Roads Dataset","full_name":"Road and Building Detection Datasets - Massachusetts Roads Dataset","num_papers_in_archive":7},{"url":"/dataset/pothole-mix","name":"Pothole Mix","full_name":"Pothole Mix Semantic Segmentation Dataset for Road Damage Detection and Segmentation","num_papers_in_archive":2},{"url":"/dataset/chesapeakersc","name":"ChesapeakeRSC","full_name":"Chesapeake Roads Spatial Context","num_papers_in_archive":1},{"url":"/dataset/polarimetric-imaging-for-perception","name":"Polarimetric Imaging for Perception","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/lane-labeling","name":"Lane Labeling"}],"parent_tasks":[{"url":"/task/semantic-segmentation","name":"Semantic Segmentation"}],"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":34,"tagged_in_all":82,"items":[{"url":"/paper/multinet-real-time-joint-semantic-reasoning","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","date":"2016-12-22","arxiv_id":"1612.07695","repositories_listed":15,"syntology":{"n":42,"n_ran":6,"n_unverified":36,"n_pointer_only":0}},{"url":"/paper/d-linknet-linknet-with-pretrained-encoder-and","title":"D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction","date":"2018-12-08","arxiv_id":null,"repositories_listed":5,"syntology":null},{"url":"/paper/enhancing-boundary-segmentation-for","title":"Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods","date":"2024-04-29","arxiv_id":"2404.18539","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":10}},{"url":"/paper/seeing-the-roads-through-the-trees-a","title":"Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery","date":"2024-01-12","arxiv_id":"2401.06762","repositories_listed":2,"syntology":null},{"url":"/paper/phileo-bench-evaluating-geo-spatial","title":"PhilEO Bench: Evaluating Geo-Spatial Foundation Models","date":"2024-01-09","arxiv_id":"2401.04464","repositories_listed":2,"syntology":null},{"url":"/paper/safe-self-attention-based-unsupervised-road","title":"SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments","date":"2020-11-27","arxiv_id":"2012.08939","repositories_listed":2,"syntology":null},{"url":"/paper/road-segmentation-using-cnn-and-distributed","title":"Road Segmentation Using CNN and Distributed LSTM","date":"2018-08-10","arxiv_id":"1808.04450","repositories_listed":2,"syntology":null},{"url":"/paper/deep-quaternion-networks","title":"Deep Quaternion Networks","date":"2017-12-13","arxiv_id":"1712.04604","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/pix2poly-a-sequence-prediction-method-for-end","title":"Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery","date":"2024-12-10","arxiv_id":"2412.07899","repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-based-road-autolabeling-with-lidar","title":"Trajectory-based Road Autolabeling with Lidar-Camera Fusion in Winter Conditions","date":"2024-12-03","arxiv_id":"2412.02370","repositories_listed":1,"syntology":null},{"url":"/paper/pathfinder-for-low-altitude-aircraft-with","title":"Pathfinder for Low-altitude Aircraft with Binary Neural Network","date":"2024-09-13","arxiv_id":"2409.08824","repositories_listed":1,"syntology":null},{"url":"/paper/rs-mamba-for-large-remote-sensing-image-dense","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","date":"2024-04-03","arxiv_id":"2404.02668","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/mmcert-provable-defense-against-adversarial","title":"MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models","date":"2024-03-28","arxiv_id":"2403.19080","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-low-level-representations-for","title":"Exploiting Low-level Representations for Ultra-Fast Road Segmentation","date":"2024-02-04","arxiv_id":"2402.02430","repositories_listed":1,"syntology":null},{"url":"/paper/ai-powered-road-network-prediction-with-multi","title":"AI Powered Road Network Prediction with Multi-Modal Data","date":"2023-12-28","arxiv_id":"2312.17040","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-extraction-of-road-networks-via","title":"Fine-Grained Extraction of Road Networks via Joint Learning of Connectivity and Segmentation","date":"2023-12-07","arxiv_id":"2312.04744","repositories_listed":1,"syntology":null},{"url":"/paper/lidar-annotation-is-all-you-need","title":"Lidar Annotation Is All You Need","date":"2023-11-08","arxiv_id":"2311.04777","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-multi-task-3mt-road-segmentation","title":"Multi-Modal Multi-Task (3MT) Road Segmentation","date":"2023-08-23","arxiv_id":"2308.11983","repositories_listed":1,"syntology":null},{"url":"/paper/atmospheric-transmission-and-thermal-inertia","title":"Atmospheric Transmission and Thermal Inertia Induced Blind Road Segmentation with a Large-Scale Dataset TBRSD","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-confidence-level-based","title":"Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation","date":"2022-11-28","arxiv_id":"2211.15066","repositories_listed":1,"syntology":null},{"url":"/paper/threshnet-segmentation-refinement-inspired-by","title":"PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization","date":"2022-11-12","arxiv_id":"2211.06560","repositories_listed":1,"syntology":null},{"url":"/paper/unstructured-road-segmentation-using","title":"Unstructured Road Segmentation using Hypercolumn based Random Forests of Local experts","date":"2022-07-23","arxiv_id":"2207.11523","repositories_listed":1,"syntology":null},{"url":"/paper/fast-road-segmentation-via-uncertainty-aware","title":"Fast Road Segmentation via Uncertainty-aware Symmetric Network","date":"2022-03-09","arxiv_id":"2203.04537","repositories_listed":1,"syntology":null},{"url":"/paper/spin-road-mapper-extracting-roads-from-aerial","title":"SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving","date":"2021-09-16","arxiv_id":"2109.07701","repositories_listed":1,"syntology":null},{"url":"/paper/stagewise-unsupervised-domain-adaptation-with","title":"Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images","date":"2021-08-28","arxiv_id":"2108.12611","repositories_listed":1,"syntology":null},{"url":"/paper/projecting-your-view-attentively-monocular","title":"Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pose-randomization-for-weakly-paired-image","title":"PREGAN: Pose Randomization and Estimation for Weakly Paired Image Style Translation","date":"2020-10-31","arxiv_id":"2011.00301","repositories_listed":1,"syntology":null},{"url":"/paper/road-segmentation-for-remote-sensing-images","title":"Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks","date":"2020-08-10","arxiv_id":"2008.04021","repositories_listed":1,"syntology":null},{"url":"/paper/roadnet-rt-high-throughput-cnn-architecture","title":"RoadNet-RT: High Throughput CNN Architecture and SoC Design for Real-Time Road Segmentation","date":"2020-06-13","arxiv_id":"2006.07644","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-semantic-map-representations-from","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","date":"2020-03-30","arxiv_id":"2003.13402","repositories_listed":1,"syntology":null}],"syntology_records":4,"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"}}