{"url":"/sota/image-super-resolution-on-pirm-test","task":{"name":"Image Super-Resolution","url":"/task/image-super-resolution","note":null},"dataset":{"name":"PIRM-test","url":"/dataset/pirm"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Image Super-Resolution** is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["NIQE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"NIQE":null}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RankSRGAN","metrics":{"NIQE":"2.51"},"uses_additional_data":false,"paper_date":"2019-08-18","paper":"/paper/ranksrgan-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/1908.06382v2","paper_title":"RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution","code":"https://github.com/xpixelgroup/ranksrgan","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"ESRGAN","metrics":{"NIQE":"2.55"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/esrgan-enhanced-super-resolution-generative","paper_url":"http://arxiv.org/abs/1809.00219v2","paper_title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","code":"https://github.com/eriklindernoren/PyTorch-GAN","n_code_links":46,"syntology":{"n_ran":8,"n_unverified":36,"n_samples":44,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"SRGAN","metrics":{"NIQE":"2.71"},"uses_additional_data":false,"paper_date":"2016-09-15","paper":"/paper/photo-realistic-single-image-super-resolution","paper_url":"http://arxiv.org/abs/1609.04802v5","paper_title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":140,"syntology":{"n_ran":16,"n_unverified":56,"n_samples":72,"n_pointer_only_licence":11}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":24,"n_unverified":92,"n_samples":116,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":24,"n_unverified":92,"n_samples":116,"n_pointer_only_licence":11,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}