{"url":"/dataset/raindrop","name":"Raindrop","full_name":null,"description_markdown":"Raindrop is a set of image pairs, where\r\neach pair contains exactly the same background scene, yet\r\none is degraded by raindrops and the other one is free from\r\nraindrops. To obtain this, the images are captured through two pieces of exactly the\r\nsame glass: one sprayed with water, and the other is left\r\nclean. The dataset consists of 1,119 pairs of images, with various\r\nbackground scenes and raindrops. They were captured with a Sony A6000\r\nand a Canon EOS 60.\r\n\r\nSource: [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](/paper/attentive-generative-adversarial-network-for)","description_withheld":null,"homepage":"https://rui1996.github.io/raindrop/raindrop_removal.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/attentive-generative-adversarial-network-for","title":"Attentive Generative Adversarial Network for Raindrop Removal from a Single Image","first_author":"Rui Qian","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Restoration","url":"/task/image-restoration","datasets_with_task":"/datasets/task/image-restoration"},{"name":"Rain Removal","url":"/task/rain-removal","datasets_with_task":"/datasets/task/rain-removal"},{"name":"Single Image Deraining","url":"/task/single-image-deraining","datasets_with_task":"/datasets/task/single-image-deraining"}],"languages":[],"variants":["Raindrop"],"data_loaders":[{"repo":"https://github.com/JHL-HUST/IBCLN","url":"https://github.com/JHL-HUST/IBCLN","frameworks":["pytorch"]}],"num_papers_in_archive":120,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/single-image-deraining-on-raindrop","task":"Single Image Deraining","dataset_variant":"Raindrop","rows":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"TransWeather","paper":"/paper/transweather-transformer-based-restoration-of","metrics":{"PSNR":"34.55"},"code_links":[{"title":"jeya-maria-jose/TransWeather","url":"https://github.com/jeya-maria-jose/TransWeather"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"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":"2026-09-24T18:15:14+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/restoring-vision-in-adverse-weather","title":"Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models","date":"2022-07-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transweather-transformer-based-restoration-of","title":"TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions","date":"2021-11-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":17,"samples_ran":14,"samples_unverified":3,"pointer_only_for_licence":5,"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."}