{"url":"/dataset/drealsr","name":"DRealSR","full_name":"Diverse Real-world image Super-Resolution","description_markdown":"DRealSR establishes a Super Resolution (SR) benchmark with diverse real-world degradation processes, mitigating the limitations of conventional simulated image degradation. \r\n\r\nIt has been collected from five DSLR cameras in natural scenes and cover indoor and outdoor scenes avoiding moving objects, e.g., advertising posters, plants, offices, buildings. The training images are cropped into 380×380, 272×272 and 192×192 patches, resulting in 31,970 patches.\r\n\r\n\r\nSource: [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://arxiv.org/abs/2008.01928)","description_withheld":null,"homepage":"https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution","introduced_date":"2020-08-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/component-divide-and-conquer-for-real-world","title":"Component Divide-and-Conquer for Real-World Image Super-Resolution","first_author":"Pengxu Wei","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Super-Resolution","url":"/task/super-resolution","datasets_with_task":"/datasets/task/super-resolution"},{"name":"Image Super-Resolution","url":"/task/image-super-resolution","datasets_with_task":"/datasets/task/image-super-resolution"},{"name":"Blind Super-Resolution","url":"/task/blind-super-resolution","datasets_with_task":"/datasets/task/blind-super-resolution"},{"name":"SSIM","url":"/task/ssim","datasets_with_task":"/datasets/task/ssim"}],"languages":[],"variants":["DRealSR"],"data_loaders":[{"repo":"https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution","url":"https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution","frameworks":["pytorch"]}],"num_papers_in_archive":36,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/blind-super-resolution-on-drealsr","task":"Blind Super-Resolution","dataset_variant":"DRealSR","rows":1,"metrics":["clipiqa","maniqa","musiq"],"first_row_in_archive_order":{"model":"SeeSR+RFSR","paper":"/paper/rfsr-improving-isr-diffusion-models-via","metrics":{"clipiqa":"0.7596","maniqa":"0.5922","musiq":"67.48"},"code_links":[{"title":"sxpro/rfsr","url":"https://github.com/sxpro/rfsr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/rfsr-improving-isr-diffusion-models-via","title":"RFSR: Improving ISR Diffusion Models via Reward Feedback Learning","date":"2024-12-04","rows_on_this_dataset":1,"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."}