{"url":"/dataset/dark-zurich","name":"Dark Zurich","full_name":null,"description_markdown":"**Dark Zurich** is an image dataset containing a total of 8779 images captured at nighttime, twilight, and daytime, along with the respective GPS coordinates of the camera for each image. These GPS annotations are used to construct cross-time-of-day correspondences, i.e., to match each nighttime or twilight image to its daytime counterpart.\r\n\r\nThese attributes allow the usage of Dark Zurich as a dataset to build models and systems that perform:\r\n\r\n1) domain adaptation (unsupervised, weakly supervised or semi-supervised), e.g. for semantic segmentation or object detection,\r\n\r\n2) image translation / style transfer to different times of day,\r\n\r\n3) robust image matching / visual localization across diverse domains, and\r\n\r\n4) other visual perception tasks that are central for autonomous vehicles and other robotic applications.","description_withheld":null,"homepage":"https://www.trace.ethz.ch/publications/2019/GCMA_UIoU/","introduced_date":"2019-01-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/semantic-nighttime-image-segmentation-with","title":"Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation","first_author":"Christos Sakaridis","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Unsupervised Semantic Segmentation","url":"/task/unsupervised-semantic-segmentation","datasets_with_task":"/datasets/task/unsupervised-semantic-segmentation"},{"name":"Source-Free Domain Adaptation","url":"/task/source-free-domain-adaptation","datasets_with_task":"/datasets/task/source-free-domain-adaptation"}],"languages":[],"variants":["Dark Zurich","Cityscapes to Dark Zurich"],"data_loaders":[],"num_papers_in_archive":57,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-dark-zurich","task":"Semantic Segmentation","dataset_variant":"Dark Zurich","rows":14,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"Refign (HRDA)","paper":"/paper/refign-align-and-refine-for-adaptation-of","metrics":{"mIoU":"63.9"},"code_links":[{"title":"brdav/refign","url":"https://github.com/brdav/refign"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/source-free-domain-adaptation-on-cityscapes-1","task":"Source-Free Domain Adaptation","dataset_variant":"Cityscapes to Dark Zurich","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CMA","paper":"/paper/contrastive-model-adaptation-for-cross","metrics":{"mIoU":"53.6"},"code_links":[{"title":"brdav/cma","url":"https://github.com/brdav/cma"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-dark","task":"Unsupervised Semantic Segmentation","dataset_variant":"Dark Zurich","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"Segmenter ViT-S/16","paper":"/paper/drive-segment-unsupervised-semantic","metrics":{"mIoU":"14.2"},"code_links":[{"title":"vobecant/DriveAndSegment","url":"https://github.com/vobecant/DriveAndSegment"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/coda-instructive-chain-of-domain-adaptation","title":"CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning","date":"2024-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contrastive-model-adaptation-for-cross","title":"Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation","date":"2023-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mic-masked-image-consistency-for-context","title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","date":"2022-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gps-glass-learning-nighttime-semantic","title":"GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data","date":"2022-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/refign-align-and-refine-for-adaptation-of","title":"Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions","date":"2022-07-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hrda-context-aware-high-resolution-domain","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","date":"2022-04-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sepico-semantic-guided-pixel-contrast-for","title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","date":"2022-04-19","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/drive-segment-unsupervised-semantic","title":"Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation","date":"2022-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/daformer-improving-network-architectures-and","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","date":"2021-11-29","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-shot-domain-adaptation-with-a-physics","title":"Zero-Shot Day-Night Domain Adaptation with a Physics Prior","date":"2021-08-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dannet-a-one-stage-domain-adaptation-network","title":"DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation","date":"2021-04-22","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/map-guided-curriculum-domain-adaptation-and","title":"Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation","date":"2020-05-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-nighttime-image-segmentation-with","title":"Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation","date":"2019-01-17","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":7,"samples_harvested":29,"samples_ran":19,"samples_unverified":10,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}