{"url":"/dataset/istd","name":"ISTD","full_name":null,"description_markdown":"The Image Shadow Triplets dataset (**ISTD**) is a dataset for shadow understanding that contains 1870 image triplets of shadow image, shadow mask, and shadow-free image.\r\n\r\nSource: [ST-CGAN: \"Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal\"](https://arxiv.org/pdf/1712.02478.pdf)\r\nImage Source: [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://paperswithcode.com/paper/stacked-conditional-generative-adversarial/)","description_withheld":null,"homepage":"https://github.com/DeepInsight-PCALab/ST-CGAN","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/stacked-conditional-generative-adversarial","title":"Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal","first_author":"Jifeng Wang","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://github.com/DeepInsight-PCALab/ST-CGAN#license"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"RGB Salient Object Detection","url":"/task/salient-object-detection","datasets_with_task":"/datasets/task/salient-object-detection"},{"name":"Shadow Removal","url":"/task/shadow-removal","datasets_with_task":"/datasets/task/shadow-removal"}],"languages":[],"variants":["ISTD"],"data_loaders":[{"repo":"https://github.com/DeepInsight-PCALab/ST-CGAN","url":"https://github.com/DeepInsight-PCALab/ST-CGAN","frameworks":[]}],"num_papers_in_archive":99,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/shadow-removal-on-istd","task":"Shadow Removal","dataset_variant":"ISTD","rows":10,"metrics":["MAE"],"first_row_in_archive_order":{"model":"ShadowFormer","paper":"/paper/shadowformer-global-context-helps-image","metrics":{"MAE":"4.79"},"code_links":[{"title":"guolanqing/shadowformer","url":"https://github.com/guolanqing/shadowformer"},{"title":"BlackJoke76/OmniSR","url":"https://github.com/BlackJoke76/OmniSR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/salient-object-detection-on-istd","task":"RGB Salient Object Detection","dataset_variant":"ISTD","rows":7,"metrics":["Balanced Error Rate"],"first_row_in_archive_order":{"model":"CPD","paper":"/paper/cascaded-partial-decoder-for-fast-and","metrics":{"Balanced Error Rate":"6.76"},"code_links":[{"title":"wuzhe71/CPD","url":"https://github.com/wuzhe71/CPD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/shadowrefiner-towards-mask-free-shadow","title":"ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer","date":"2024-04-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/resfusion-prior-residual-noise-embedded","title":"Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise","date":"2023-11-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shadowformer-global-context-helps-image","title":"ShadowFormer: Global Context Helps Image Shadow Removal","date":"2023-02-03","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dc-shadownet-single-image-hard-and-soft-1","title":"DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network","date":"2022-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spa-former-transformer-image-shadow-detection","title":"SpA-Former: Transformer image shadow detection and removal via spatial attention","date":"2022-06-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/towards-ghost-free-shadow-removal-via-dual","title":"Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN","date":"2019-11-20","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/cascaded-partial-decoder-for-fast-and","title":"Cascaded Partial Decoder for Fast and Accurate Salient Object Detection","date":"2019-04-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-bi-directional-message-passing-model-for","title":"A Bi-Directional Message Passing Model for Salient Object Detection","date":"2018-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/direction-aware-spatial-context-features-for-1","title":"Direction-aware Spatial Context Features for Shadow Detection and Removal","date":"2018-05-12","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/direction-aware-spatial-context-features-for","title":"Direction-aware Spatial Context Features for Shadow Detection","date":"2017-12-12","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/stacked-conditional-generative-adversarial","title":"Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal","date":"2017-12-07","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+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/shadow-detection-with-conditional-generative","title":"Shadow Detection With Conditional Generative Adversarial Networks","date":"2017-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/non-local-deep-features-for-salient-object","title":"Non-Local Deep Features for Salient Object Detection","date":"2017-07-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deeply-supervised-salient-object-detection","title":"Deeply supervised salient object detection with short connections","date":"2016-11-15","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/interactive-shadow-removal-and-ground-truth","title":"Interactive Shadow Removal and Ground Truth for Difficult Shadow Scenes","date":"2016-09-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":4,"samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":6,"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."}