{"url":"/sota/spectral-reconstruction-on-arad-1k","task":{"name":"Spectral Reconstruction","url":"/task/spectral-reconstruction","note":null},"dataset":{"name":"ARAD-1K","url":"/dataset/arad-1k"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"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":["PSNR","MRAE","RMSE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PSNR":"higher","MRAE":null,"RMSE":"lower"}},"counts":{"rows":11,"rows_with_code":9,"rows_with_paper_page":11,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MST++","metrics":{"MRAE":"0.1645","PSNR":"34.32","RMSE":"0.0248"},"uses_additional_data":false,"paper_date":"2022-04-17","paper":"/paper/mst-multi-stage-spectral-wise-transformer-for","paper_url":"https://arxiv.org/abs/2204.07908v1","paper_title":"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction","code":"https://github.com/cmhungsteve/Awesome-Transformer-Attention","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"MST-L","metrics":{"MRAE":"0.1772","PSNR":"33.90","RMSE":"0.0256"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/mask-guided-spectral-wise-transformer-for","paper_url":"https://arxiv.org/abs/2111.07910v2","paper_title":"Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction","code":"https://github.com/cmhungsteve/Awesome-Transformer-Attention","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MPRNet","metrics":{"MRAE":"0.1817","PSNR":"33.50","RMSE":"0.0270"},"uses_additional_data":false,"paper_date":"2021-02-04","paper":"/paper/multi-stage-progressive-image-restoration","paper_url":"https://arxiv.org/abs/2102.02808v2","paper_title":"Multi-Stage Progressive Image Restoration","code":"https://github.com/swz30/restormer","n_code_links":8,"syntology":{"n_ran":18,"n_unverified":8,"n_samples":26,"n_pointer_only_licence":25}},{"rank_in_archive_order":4,"model":"Restormer","metrics":{"MRAE":"0.1833","PSNR":"33.40","RMSE":"0.0274"},"uses_additional_data":false,"paper_date":"2021-11-18","paper":"/paper/restormer-efficient-transformer-for-high","paper_url":"https://arxiv.org/abs/2111.09881v2","paper_title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","code":"https://github.com/swz30/restormer","n_code_links":13,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":5,"model":"MIRNet","metrics":{"MRAE":"0.1890","PSNR":"33.29","RMSE":"0.0274"},"uses_additional_data":false,"paper_date":"2020-03-15","paper":"/paper/learning-enriched-features-for-real-image","paper_url":"https://arxiv.org/abs/2003.06792v2","paper_title":"Learning Enriched Features for Real Image Restoration and Enhancement","code":"https://github.com/swz30/restormer","n_code_links":12,"syntology":{"n_ran":12,"n_unverified":8,"n_samples":20,"n_pointer_only_licence":3}},{"rank_in_archive_order":6,"model":"HINet","metrics":{"MRAE":"0.2032","PSNR":"32.51","RMSE":"0.0303"},"uses_additional_data":false,"paper_date":"2021-05-13","paper":"/paper/hinet-half-instance-normalization-network-for","paper_url":"https://arxiv.org/abs/2105.06086v2","paper_title":"HINet: Half Instance Normalization Network for Image Restoration","code":"https://github.com/megvii-model/HINet","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"HDNet","metrics":{"MRAE":"0.2048","PSNR":"32.13","RMSE":"0.0317"},"uses_additional_data":false,"paper_date":"2022-03-04","paper":"/paper/hdnet-high-resolution-dual-domain-learning","paper_url":"https://arxiv.org/abs/2203.02149v2","paper_title":"HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging","code":"https://github.com/caiyuanhao1998/MST","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"AWAN","metrics":{"MRAE":"0.2500","PSNR":"31.22","RMSE":"0.0367"},"uses_additional_data":false,"paper_date":"2022-01-18","paper":"/paper/adaptive-weighted-guided-image-filtering-for","paper_url":"https://arxiv.org/abs/2201.06823v1","paper_title":"Adaptive Weighted Guided Image Filtering for Depth Enhancement in Shape-From-Focus","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"EDSR","metrics":{"MRAE":"0.3277","PSNR":"28.29","RMSE":"0.0437"},"uses_additional_data":false,"paper_date":"2017-07-10","paper":"/paper/enhanced-deep-residual-networks-for-single","paper_url":"http://arxiv.org/abs/1707.02921v1","paper_title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","code":"https://github.com/sanghyun-son/EDSR-PyTorch","n_code_links":45,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":2}},{"rank_in_archive_order":10,"model":"HRNet","metrics":{"MRAE":"0.3476","PSNR":"26.89","RMSE":"0.0550"},"uses_additional_data":false,"paper_date":"2020-05-10","paper":"/paper/hierarchical-regression-network-for-spectral","paper_url":"https://arxiv.org/abs/2005.04703v1","paper_title":"Hierarchical Regression Network for Spectral Reconstruction from RGB Images","code":"https://github.com/zhaoyuzhi/Hierarchical-Regression-Network-for-Spectral-Reconstruction-from-RGB-Images","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"HSCNN+","metrics":{"MRAE":"0.3814","PSNR":"26.36","RMSE":"0.0588"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/hscnn-a-hybrid-siamese-convolutional-neural","paper_url":"https://aclanthology.org/2020.emnlp-main.545","paper_title":"HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":7,"samples_over_distinct_papers":{"n_ran":48,"n_unverified":18,"n_samples":66,"n_pointer_only_licence":37,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":48,"n_unverified":18,"n_samples":66,"n_pointer_only_licence":37,"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"}}}