{"url":"/dataset/s-coco","name":"S-COCO","full_name":"Synthetic COCO","description_markdown":"Synthetic COCO (S-COCO) is a synthetically created dataset for homography estimation learning. It was introduced by DeTone et al., where the source and target images are generated by duplicating the same COCO image. The source patch $I_S$ is generated by randomly cropping a source candidate at position $p$ with a size of 128 ×128 pixels. Then the patch’s corners are randomly perturbed vertically and horizontally by values within the range [−$\\rho$,$\\rho$] and the four correspondences define a homography $H_{ST}$ . The inverse of this homography $H_{TS} = (H_{ST} )^{-1}$ is applied to the target candidate and from the resulted warped image a target patch $I_T$ is cropped at the same location p. Both $I_S$ and $I_T$ are the input data with the homography $H_{ST}$ as ground truth.","description_withheld":null,"homepage":"","introduced_date":"2016-06-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-image-homography-estimation","title":"Deep Image Homography Estimation","first_author":"Daniel DeTone","url":null},"license":{"name":"Custom","url":"https://cocodataset.org/#termsofuse"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Homography Estimation","url":"/task/homography-estimation","datasets_with_task":"/datasets/task/homography-estimation"}],"languages":[],"variants":["S-COCO"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/homography-estimation-on-s-coco","task":"Homography Estimation","dataset_variant":"S-COCO","rows":5,"metrics":["MACE"],"first_row_in_archive_order":{"model":"PFNet","paper":"/paper/rethinking-planar-homography-estimation-using","metrics":{"MACE":"1.73"},"code_links":[{"title":"ruizengalways/PFNet","url":"https://github.com/ruizengalways/PFNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/perceptual-loss-for-robust-unsupervised","title":"Perceptual Loss for Robust Unsupervised Homography Estimation","date":"2021-04-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/content-aware-unsupervised-deep-homography","title":"Content-Aware Unsupervised Deep Homography Estimation","date":"2019-09-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-planar-homography-estimation-using","title":"Rethinking Planar Homography Estimation Using Perspective Fields","date":"2019-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-deep-homography-a-fast-and","title":"Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model","date":"2017-09-12","rows_on_this_dataset":1,"code_links":3,"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/deep-image-homography-estimation","title":"Deep Image Homography Estimation","date":"2016-06-13","rows_on_this_dataset":1,"code_links":8,"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."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":4,"samples_harvested":10,"samples_ran":4,"samples_unverified":6,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"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."}