{"url":"/sota/multi-frame-super-resolution-on-proba-v","task":{"name":"Multi-Frame Super-Resolution","url":"/task/multi-frame-super-resolution","note":null},"dataset":{"name":"PROBA-V","url":"/dataset/proba-v"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"When multiple images of the same view are taken from slightly different positions, perhaps also at different times, then they collectively contain more information than any single image on its own. Multi-Frame Super-Resolution fuses these low-res inputs into a composite high-res image that can reveal some of the original detail that cannot be recovered from any low-res image alone.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Credit: [HighRes-net](https://github.com/ElementAI/HighRes-net) )</span>","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":["Normalized cPSNR"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Normalized cPSNR":null}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TR-MISR","metrics":{"Normalized cPSNR":"0.9300466898779116"},"uses_additional_data":false,"paper_date":"2022-02-05","paper":"/paper/tr-misr-multiimage-super-resolution-based-on","paper_url":"https://ieeexplore.ieee.org/abstract/document/9684717","paper_title":"TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers","code":"https://github.com/Suanmd/TR-MISR","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PIUnet","metrics":{"Normalized cPSNR":"0.9313717296835213"},"uses_additional_data":false,"paper_date":"2021-05-26","paper":"/paper/permutation-invariance-and-uncertainty-in","paper_url":"https://arxiv.org/abs/2105.12409v1","paper_title":"Permutation invariance and uncertainty in multitemporal image super-resolution","code":"https://github.com/diegovalsesia/piunet","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"RAMS","metrics":{"Normalized cPSNR":"0.9336790819983855"},"uses_additional_data":false,"paper_date":"2020-07-06","paper":"/paper/multi-image-super-resolution-of-remotely","paper_url":"https://arxiv.org/abs/2007.03107v2","paper_title":"Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networks","code":"https://github.com/isaaccorley/torchrs","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"WDSR-MFSR","metrics":{"Normalized cPSNR":"0.9411827883122681"},"uses_additional_data":false,"paper_date":"2018-08-27","paper":"/paper/wide-activation-for-efficient-and-accurate","paper_url":"http://arxiv.org/abs/1808.08718v2","paper_title":"Wide Activation for Efficient and Accurate Image Super-Resolution","code":"https://github.com/krasserm/super-resolution","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":17,"n_samples":17,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"3DWDSR","metrics":{"Normalized cPSNR":"0.9462525077016232"},"uses_additional_data":false,"paper_date":"2018-08-27","paper":"/paper/wide-activation-for-efficient-and-accurate","paper_url":"http://arxiv.org/abs/1808.08718v2","paper_title":"Wide Activation for Efficient and Accurate Image Super-Resolution","code":"https://github.com/krasserm/super-resolution","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":17,"n_samples":17,"n_pointer_only_licence":2}},{"rank_in_archive_order":6,"model":"HighRes-net","metrics":{"Normalized cPSNR":"0.947388637793901"},"uses_additional_data":false,"paper_date":"2020-02-15","paper":"/paper/highres-net-recursive-fusion-for-multi-frame","paper_url":"https://arxiv.org/abs/2002.06460v1","paper_title":"HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery","code":"https://github.com/ElementAI/HighRes-net","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"HighRes-net","metrics":{"Normalized cPSNR":"0.947388637793901"},"uses_additional_data":false,"paper_date":"2020-01-01","paper":"/paper/highres-net-multi-frame-super-resolution-by","paper_url":"https://openreview.net/forum?id=HJxJ2h4tPr","paper_title":"HighRes-net: Multi-Frame Super-Resolution by Recursive Fusion","code":"https://github.com/ElementAI/HighRes-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"DeepSUM","metrics":{"Normalized cPSNR":"0.948844910272775"},"uses_additional_data":false,"paper_date":"2019-07-15","paper":"/paper/deepsum-deep-neural-network-for-super","paper_url":"https://arxiv.org/abs/1907.06490v2","paper_title":"DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal images","code":"https://github.com/diegovalsesia/deepsum","n_code_links":1,"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":3,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":25,"n_samples":25,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":42,"n_samples":42,"n_pointer_only_licence":4,"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"}}}