{"url":"/dataset/ins-dataset","name":"INS Dataset","full_name":null,"description_markdown":"A significant challenge in removing shadows from indoor scenes is obtaining shadow-free images. To overcome this challenge, we propose a novel rendering pipeline for generating shadowed and shadow-free images under direct and indirect illumination, and create a comprehensive synthetic dataset that contains over 30,000 image pairs, covering various object types and lighting conditions.\r\n\r\nWe implemented a direct/indirect shadow and shadow-free rendering pipeline using Blender Cycles engine, with the help of Open Shading Language (OSL). The resulting collection of shadow and shadow-free images is referred to as the “INS dataset”. The dataset includes 30,000 training and 2,000 testing images, all with a resolution of 512 × 512. The training and testing images are generated from distinct scenes with different objects and materials.","description_withheld":null,"homepage":"https://blackjoke76.github.io/Projects/OmniSR/","introduced_date":"2024-10-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/omnisr-shadow-removal-under-direct-and","title":"OmniSR: Shadow Removal under Direct and Indirect Lighting","first_author":"Jiamin Xu","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Shadow Removal","url":"/task/shadow-removal","datasets_with_task":"/datasets/task/shadow-removal"},{"name":"Shadow Detection","url":"/task/shadow-detection","datasets_with_task":"/datasets/task/shadow-detection"},{"name":"Image Shadow Removal","url":"/task/image-shadow-removal","datasets_with_task":"/datasets/task/image-shadow-removal"}],"languages":[],"variants":["INS Dataset"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-shadow-removal-on-ins-dataset","task":"Image Shadow Removal","dataset_variant":"INS Dataset","rows":1,"metrics":["Average PSNR (dB)"],"first_row_in_archive_order":{"model":"OmniSR","paper":"/paper/omnisr-shadow-removal-under-direct-and","metrics":{"Average PSNR (dB)":"30.38"},"code_links":[{"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/shadow-removal-on-ins-dataset","task":"Shadow Removal","dataset_variant":"INS Dataset","rows":1,"metrics":["Average PSNR (dB)"],"first_row_in_archive_order":{"model":"OmniSR","paper":"/paper/omnisr-shadow-removal-under-direct-and","metrics":{"Average PSNR (dB)":"30.38"},"code_links":[{"title":"BlackJoke76/OmniSR","url":"https://github.com/BlackJoke76/OmniSR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/omnisr-shadow-removal-under-direct-and","title":"OmniSR: Shadow Removal under Direct and Indirect Lighting","date":"2024-10-02","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}