{"url":"/dataset/sidl-smartphone-images-with-dirty-lenses","name":"SIDL: A Real-World Dataset for Restoring Smartphone Images with Dirty Lenses","full_name":null,"description_markdown":"Smartphone cameras are ubiquitous in daily life, yet their performance can be severely impacted by dirty lenses, leading to degraded image quality. \r\nThis issue is often overlooked in image restoration research, which assumes ideal or controlled lens conditions. \r\nTo address this gap, we introduced SIDL (Smartphone Images with Dirty Lenses), a novel dataset designed to restore images captured through contaminated smartphone lenses. \r\nSIDL contains diverse real-world images taken under various lighting conditions and environments. \r\nThese images feature a wide range of lens contaminants, including water drops, fingerprints, and dust. \r\nEach contaminated image is paired with a clean reference image, enabling supervised learning approaches for restoration tasks.\r\nTo evaluate the challenge posed by SIDL, various state-of-the-art restoration models were trained and compared on this dataset. \r\nTheir performances achieved some level of restoration but did not adequately address the diverse and realistic nature of the lens contaminants in SIDL.\r\nThis challenge highlights the need for more robust and adaptable image restoration techniques for restoring images with dirty lenses.\r\nProject website: https://sidl-benchmark.github.io\r\n\r\nSource : [SIDL: A Real-World Dataset for Restoring Smartphone Images with Dirty Lenses](https://doi.org/10.1609/aaai.v39i3.32257)","description_withheld":null,"homepage":"https://sidl-benchmark.github.io/","introduced_date":"2025-04-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/sidl-a-real-world-dataset-for-restoring","title":"SIDL: A Real-World Dataset for Restoring Smartphone Images with Dirty Lenses","first_author":"Sooyoung Choi","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Restoration","url":"/task/image-restoration","datasets_with_task":"/datasets/task/image-restoration"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SIDL: A Real-World Dataset for Restoring Smartphone Images with Dirty Lenses"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}