{"url":"/sota/deblurring-on-dvd-1","task":{"name":"Deblurring","url":"/task/deblurring","note":null},"dataset":{"name":"DVD","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Deblurring** is a computer vision task that involves removing the blurring artifacts from images or videos to restore the original, sharp content. Blurring can be caused by various factors such as camera shake, fast motion, and out-of-focus objects, and can result in a loss of detail and quality in the captured images. The goal of deblurring is to produce a clear, high-quality image that accurately represents the original scene.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks](https://arxiv.org/pdf/1907.13106v1.pdf) )</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":["PSNR","SSIM"],"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","SSIM":"higher"}},"counts":{"rows":7,"rows_with_code":6,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"BSSTNet","metrics":{"PSNR":"34.95","SSIM":"0.9703"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/blur-aware-spatio-temporal-sparse-transformer","paper_url":"https://arxiv.org/abs/2406.07551v1","paper_title":"Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring","code":"https://github.com/huicongzhang/bsstnet","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":17}},{"rank_in_archive_order":2,"model":"RVRT","metrics":{"PSNR":"34.92","SSIM":"97.38"},"uses_additional_data":false,"paper_date":"2022-06-05","paper":"/paper/recurrent-video-restoration-transformer-with","paper_url":"https://arxiv.org/abs/2206.02146v3","paper_title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","code":"https://github.com/jingyunliang/rvrt","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":5}},{"rank_in_archive_order":3,"model":"GShift-Net","metrics":{"PSNR":"34.69","SSIM":"0.969"},"uses_additional_data":false,"paper_date":"2022-06-22","paper":"/paper/no-attention-is-needed-grouped-spatial","paper_url":"https://arxiv.org/abs/2206.10810v2","paper_title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","code":"https://github.com/dasongli1/shift-net","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"VRT","metrics":{"PSNR":"34.27"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/vrt-a-video-restoration-transformer","paper_url":"https://arxiv.org/abs/2201.12288v2","paper_title":"VRT: A Video Restoration Transformer","code":"https://github.com/jingyunliang/vrt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":5,"model":"FGST","metrics":{"PSNR":"33.50"},"uses_additional_data":false,"paper_date":"2022-01-06","paper":"/paper/flow-guided-sparse-transformer-for-video","paper_url":"https://arxiv.org/abs/2201.01893v3","paper_title":"Flow-Guided Sparse Transformer for Video Deblurring","code":"https://github.com/linjing7/VR-Baseline","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"STDAN","metrics":{"PSNR":"33.05","SSIM":"0.9374"},"uses_additional_data":false,"paper_date":"2022-07-22","paper":"/paper/spatio-temporal-deformable-attention-network","paper_url":"https://arxiv.org/abs/2207.10852v1","paper_title":"Spatio-Temporal Deformable Attention Network for Video Deblurring","code":"https://github.com/huicongzhang/stdan","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"MB2D","metrics":{"PSNR":"32.34"},"uses_additional_data":true,"paper_date":"2020-12-23","paper":"/paper/blur-more-to-deblur-better-multi-blur2deblur","paper_url":"https://arxiv.org/abs/2012.12507v1","paper_title":"Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring","code":null,"n_code_links":0,"syntology":null}],"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":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":30,"n_unverified":20,"n_samples":50,"n_pointer_only_licence":28,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":30,"n_unverified":20,"n_samples":50,"n_pointer_only_licence":28,"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"}}}