{"doi":"10.1109/cvpr.2016.350","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","abstract":"Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations, 20 000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.","journal":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":2016,"id":8132,"datarank":19.08426993929529,"base_score":9.355565624128962,"endowment":9.355565624128962,"self_citation_contribution":1.4033348436193445,"citation_network_contribution":17.680935095675945,"self_endowment_contribution":1.4033348436193445,"citer_contribution":17.680935095675945,"corpus_percentile":99.8,"corpus_rank":903,"citation_count":11562,"citer_count":197,"citers_with_citation_signal":197,"citers_with_endowment":197,"datacite_reuse_total":0,"is_dataset":true,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2016-06-01","authors":[{"id":72214,"name":"Mohamed Omran","orcid":null,"position":1,"is_corresponding":false},{"id":72215,"name":"Sebastian Ramos","orcid":null,"position":2,"is_corresponding":false},{"id":72216,"name":"Timo Rehfeld","orcid":null,"position":3,"is_corresponding":false},{"id":72217,"name":"Markus Enzweiler","orcid":"0000-0001-9211-9882","position":4,"is_corresponding":false},{"id":66244,"name":"Rodrigo Benenson","orcid":null,"position":5,"is_corresponding":false},{"id":72218,"name":"Uwe Franke","orcid":null,"position":6,"is_corresponding":false},{"id":72219,"name":"Stefan Roth","orcid":"0000-0001-9002-9832","position":7,"is_corresponding":false},{"id":66245,"name":"Bernt Schiele","orcid":"0000-0001-9683-5237","position":8,"is_corresponding":false},{"id":72213,"name":"Marius Cordts","orcid":"0000-0001-8729-9233","position":0,"is_corresponding":true}],"reference_count":82,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}